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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating convenience or simplicity in actions or tasks

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

    "easy" followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    expressions of ease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.78
    AccessorTable
    -0.73
    GEBURTSDATUM
    -0.67
    WireFormatLite
    -0.66
     ModelExpression
    -0.66
     Universitaria
    -0.63
    ="#"><
    -0.63
    randomUUID
    -0.62
     ProtoMessage
    -0.62
    featureID
    -0.61
    POSITIVE LOGITS
    EASY
    1.00
     access
    0.95
     Easy
    0.94
    Easy
    0.92
     easy
    0.90
     breezy
    0.89
     EASY
    0.88
    easy
    0.84
     kolay
    0.81
    going
    0.80
    Act Density 0.082%

    No Known Activations