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

    Neuronpedia

    INDEX
    Explanations

    Comparisons and durations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pace
    -0.09
     باللغة
    -0.08
     لدي
    -0.08
    antenimiento
    -0.08
    ानदार
    -0.07
     Prin
    -0.07
     kisses
    -0.07
    aneous
    -0.07
    zetten
    -0.07
    _speed
    -0.07
    POSITIVE LOGITS
     decades
    0.20
    几十
    0.16
     décadas
    0.14
     centuries
    0.12
     दशक
    0.11
     Jahrze
    0.11
     दश
    0.11
     décennies
    0.11
     वर्षों
    0.10
    -century
    0.10
    Act Density 0.036%

    No Known Activations