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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Resolve
    -0.07
    .Redirect
    -0.07
     reluctant
    -0.07
    .increment
    -0.07
    .e
    -0.07
    _override
    -0.07
    '.↵
    -0.07
    dimensions
    -0.06
     �
    -0.06
     positivity
    -0.06
    POSITIVE LOGITS
    ワイ
    0.08
    fh
    0.07
    茶叶
    0.07
     сериал
    0.07
     기타
    0.07
    麻烦
    0.07
     сами
    0.07
     Utf
    0.07
     книги
    0.07
    arf
    0.06
    Act Density 0.010%

    No Known Activations