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

    Neuronpedia

    INDEX
    Explanations

    phrases related to functionalities and capabilities of systems or objects

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

    explains which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ‘
    -0.52
    ’
    -0.47
     he
    -0.47
     co
    -0.46
     t
    -0.44
     Per
    -0.44
    )}</
    -0.44
     '
    -0.43
     “
    -0.42
    ']
    -0.41
    POSITIVE LOGITS
    aarrggbb
    1.10
     typelib
    1.09
    parsedMessage
    0.92
    المشاركات
    0.89
    RenderAtEndOf
    0.87
    Personensuche
    0.84
     صوتيه
    0.83
    styleType
    0.82
     Infórmanos
    0.82
     createState
    0.80
    Act Density 0.002%

    No Known Activations