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

    Neuronpedia

    INDEX
    Explanations

    radio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    準備
    -0.08
    뷴
    -0.08
     fades
    -0.07
     לראש
    -0.07
    Hop
    -0.07
    ((&
    -0.06
     stickers
    -0.06
    ご覧
    -0.06
     mour
    -0.06
     باستخدام
    -0.06
    POSITIVE LOGITS
    �
    0.08
    .abstract
    0.08
    reverse
    0.07
    psych
    0.07
    modify
    0.07
    寄せ
    0.06
    主义
    0.06
     rationale
    0.06
    탤
    0.06
    position
    0.06
    Act Density 0.007%

    No Known Activations