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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical quantities and dimensions in various contexts

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

    Large numerical values followed by a descriptor

    np_acts-logits-general · gemini-2.0-flash

    millions of fans members pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    delning
    -0.55
     Chwiliwch
    -0.52
     coppia
    -0.48
    лат
    -0.47
    ActionButton
    -0.46
     Sélectionnez
    -0.44
     hiperten
    -0.44
     deux
    -0.43
     gole
    -0.43
    şiv
    -0.43
    POSITIVE LOGITS
    TagMode
    0.82
    NUMX
    0.78
    Portale
    0.76
     (!)
    0.76
    + 
    0.71
    BeginContext
    0.71
    InitVars
    0.70
    ^(@)
    0.70
     total
    0.69
     MotionEvent
    0.69
    Act Density 0.303%

    No Known Activations