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

    Neuronpedia

    INDEX
    Explanations

    family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    纭
    0.44
    လည်း
    0.43
     त्यांच्या
    0.42
    如果你
    0.42
    男女
    0.42
    如果您
    0.42
     ваших
    0.41
    计数
    0.41
     seus
    0.41
    你可以
    0.40
    POSITIVE LOGITS
    ma
    0.40
     (
    0.40
     Ma
    0.39
    .
    0.38
    ,
    0.37
     ISBN
    0.37
    ahan
    0.37
     Samuel
    0.36
     LLC
    0.36
    '
    0.36
    Act Density 0.020%

    No Known Activations