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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (robot
    -0.07
    页面
    -0.07
     realmente
    -0.06
    _env
    -0.06
     fet
    -0.06
    .addColumn
    -0.06
    .palette
    -0.06
    _fh
    -0.06
    :host
    -0.06
     paths
    -0.06
    POSITIVE LOGITS
    يار
    0.07
    ῆς
    0.07
    .way
    0.07
     exterior
    0.07
     beware
    0.07
     наблюд
    0.06
     返回
    0.06
    _WEEK
    0.06
     brewers
    0.06
     NUM
    0.06
    Act Density 0.011%

    No Known Activations