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

    Neuronpedia

    INDEX
    Explanations

    references to programming languages, frameworks, and their built-in functionalities

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

    Code, libraries, or built-in functions

    np_acts-logits-general · gemini-2.0-flash

    built-in API and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.57
     mijne
    -0.52
    帖最后由
    -0.50
     validamos
    -0.49
    ſcher
    -0.49
     HFILL
    -0.47
    iNdEx
    -0.47
     feroit
    -0.45
    Спољашње
    -0.44
     tartalomajánló
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.50
     built
    0.43
     Microsoft
    0.41
     tools
    0.41
    Built
    0.38
    Microsoft
    0.38
     tool
    0.38
     available
    0.36
     Built
    0.36
     BUILT
    0.36
    Act Density 1.104%

    No Known Activations