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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons and contrasts between different subjects or entities

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

    original, previous, many, other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.44
    ">//
    -0.43
    PreExecute
    -0.43
    ="@+
    -0.43
    titleMargin
    -0.38
     nakalista
    -0.36
    encodeWith
    -0.36
    InitStruct
    -0.35
    unknownFields
    -0.35
     DEMAND
    -0.35
    POSITIVE LOGITS
     colonias
    0.46
     naciones
    0.40
    tonode
    0.40
    AutoModerator
    0.40
     grueso
    0.40
     يتيمه
    0.40
     cantantes
    0.40
    ]={
    0.40
     conductas
    0.39
     bouche
    0.39
    Act Density 0.092%

    No Known Activations