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

    Neuronpedia

    INDEX
    Explanations

    univers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adjustment
    -0.08
    规模化
    -0.08
    占领
    -0.08
    _LEFT
    -0.08
    监管
    -0.07
    Ỏ
    -0.07
    .state
    -0.07
     فإذا
    -0.07
    .Filter
    -0.07
    cloud
    -0.07
    POSITIVE LOGITS
    _('
    0.08
    ⋄
    0.07
     לגרום
    0.07
    ⅀
    0.06
    �
    0.06
    ")(
    0.06
    עמ
    0.06
    anneer
    0.06
    ,res
    0.06
    $table
    0.06
    Act Density 0.041%

    No Known Activations