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

    Neuronpedia

    INDEX
    Explanations

    assertions for equality and truthiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Henderson
    0.41
     Daphne
    0.40
    ampoo
    0.39
    scape
    0.39
     frances
    0.39
     Franc
    0.38
     Hall
    0.38
    颈
    0.38
     संपूर्ण
    0.38
    الي
    0.38
    POSITIVE LOGITS
    Equal
    0.78
     equal
    0.71
     égal
    0.71
     Equal
    0.70
     Gleich
    0.66
    equal
    0.66
    False
    0.64
     igualdad
    0.63
     равен
    0.61
    NotNull
    0.59
    Act Density 0.003%

    No Known Activations