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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

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

    0.5 followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PullParser
    -0.63
     الرياضيه
    -0.57
     ArrayAdapter
    -0.56
     ſich
    -0.55
    printStackTrace
    -0.54
    getJSONArray
    -0.52
    olescence
    -0.52
    jandro
    -0.52
    BeginContext
    -0.51
     "..\..\
    -0.50
    POSITIVE LOGITS
    half
    0.80
    Half
    0.73
     half
    0.71
     Half
    0.67
     HALF
    0.63
    HALF
    0.59
     setengah
    0.53
     halben
    0.50
    一半
    0.48
    半分
    0.46
    Act Density 0.093%

    No Known Activations