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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and quantities

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

    Numbers followed by specific units or categories

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.85
     houſe
    -0.76
     purpoſe
    -0.74
     Majefty
    -0.71
     caufe
    -0.71
     مرئيه
    -0.71
     متعلقه
    -0.69
    sidemargin
    -0.69
    BeginContext
    -0.69
     fometimes
    -0.68
    POSITIVE LOGITS
     distinct
    0.56
    Executives
    0.55
    つの
    0.55
    うち
    0.55
     separate
    0.51
    fold
    0.51
    ох
    0.51
     different
    0.51
    不同的
    0.50
     प्रकार
    0.48
    Act Density 0.438%

    No Known Activations