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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    首家
    -0.07
    .likes
    -0.07
    _der
    -0.07
    既
    -0.07
    .lastName
    -0.07
     mills
    -0.06
    _VALUE
    -0.06
    睹
    -0.06
    ➩
    -0.06
    -vis
    -0.06
    POSITIVE LOGITS
    ㌃
    0.07
     frais
    0.07
     ragazzi
    0.07
    .Set
    0.07
    $self
    0.07
    enko
    0.07
    崧
    0.06
     Sunny
    0.06
    יכות
    0.06
    ستطيع
    0.06
    Act Density 0.001%

    No Known Activations