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

    Neuronpedia

    INDEX
    Explanations

    tackles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .escape
    -0.07
    ("***
    -0.07
    .bulk
    -0.07
    韧性
    -0.07
    .Tasks
    -0.07
    .ch
    -0.07
    Ժ
    -0.07
     истории
    -0.06
    .mContext
    -0.06
    _SOURCE
    -0.06
    POSITIVE LOGITS
    nąć
    0.08
     Deliver
    0.08
     Median
    0.07
     raped
    0.07
    Daniel
    0.07
    沙发
    0.07
    فرض
    0.07
     כאן
    0.07
    [cnt
    0.06
     Via
    0.06
    Act Density 0.003%

    No Known Activations