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

    Neuronpedia

    INDEX
    Explanations

    prompts for continuing or reading more content

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

    Followed by continuation markers

    np_acts-logits-general · gemini-2.0-flash

    continue reading links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.79
    orghini
    -0.79
    Cyfeiriadau
    -0.78
    CppCodeGen
    -0.77
    '):
    -0.75
     Waray
    -0.74
     itſelf
    -0.74
     $_"
    -0.73
    EndInit
    -0.73
    OGND
    -0.73
    POSITIVE LOGITS
    :
    0.99
    ↵↵
    0.60
     »
    0.60
    ：
    0.55
    ↵
    0.54
    !
    0.51
    »
    0.50
    ↵↵↵
    0.48
    ↵↵↵↵
    0.48
    >>>
    0.48
    Act Density 0.109%

    No Known Activations