Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical details about processes and methodologies in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Conditions, processes, procedures, or steps

    np_acts-logits-general · gemini-2.0-flash

    process conditions and optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dAtA
    -0.53
    styleable
    -0.49
     Вікі
    -0.49
    MessageOf
    -0.47
     Wikimedijinoj
    -0.46
     wireType
    -0.44
     Савезне
    -0.44
     télécommande
    -0.44
    ghijklmnop
    -0.44
    pulumi
    -0.43
    POSITIVE LOGITS
    procedures
    0.58
     procedures
    0.58
     procedure
    0.52
     processes
    0.50
    recipe
    0.50
     Processes
    0.49
    processes
    0.49
     techniques
    0.49
     Procedures
    0.48
    procedure
    0.48
    Act Density 0.991%

    No Known Activations