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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and reflections on personal experiences

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

    internal states and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.47
    bnf
    -0.42
    Atentamente
    -0.41
    Personendaten
    -0.39
     consommate
    -0.39
     Mitteln
    -0.38
    zaron
    -0.38
     equivalents
    -0.36
     parezca
    -0.36
     Cientí
    -0.36
    POSITIVE LOGITS
     HasFactory
    0.65
    testify
    0.47
     Knot
    0.46
    Knot
    0.44
    évaluateur
    0.42
    AxisAlignment
    0.40
    CPP
    0.40
     knot
    0.40
     save
    0.40
     Calculus
    0.39
    Act Density 0.075%

    No Known Activations