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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated context, particularly in technical or formal discussions

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

    numerical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.64
    rawDesc
    -0.63
    SharedCtor
    -0.61
    -0.60
     lenker
    -0.60
     HasFactory
    -0.59
    gameserver
    -0.59
    ArrowToggle
    -0.58
    AsUp
    -0.57
    */].
    -0.57
    POSITIVE LOGITS
    ↵
    0.35
     dintr
    0.34
     Navidad
    0.33
     dragón
    0.32
    Non
    0.32
     poly
    0.31
    Merry
    0.31
    PREFERRED
    0.30
    bahnen
    0.30
     Pyrr
    0.29
    Act Density 0.204%

    No Known Activations