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
     upstream
    -0.08
     in
    -0.07
    즙
    -0.07
    vote
    -0.07
    <Route
    -0.07
     Ко
    -0.06
    ˓
    -0.06
    �
    -0.06
    ;↵↵↵
    -0.06
    Producto
    -0.06
    POSITIVE LOGITS
    潜能
    0.07
     торр
    0.07
    קטגוריה
    0.07
     buộc
    0.07
     مدير
    0.07
     wrześ
    0.07
    巨
    0.07
    (_.
    0.07
    _put
    0.07
     erv
    0.07
    Act Density 0.004%

    No Known Activations