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

    Neuronpedia

    INDEX
    Explanations

    qualities and evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    će
    0.40
    ff
    0.36
    airy
    0.36
    ível
    0.36
    stri
    0.35
    δη
    0.35
     உரி
    0.35
    таў
    0.35
    lık
    0.34
    ts
    0.34
    POSITIVE LOGITS
     anguish
    0.46
    विद्यालय
    0.43
     affirming
    0.42
     wundersch
    0.42
     hechos
    0.42
     ቲ
    0.42
     hospitales
    0.41
    優しい
    0.41
     ecma
    0.40
    Ecole
    0.40
    Act Density 0.001%

    No Known Activations