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

    Neuronpedia

    INDEX
    Explanations

    website addresses and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SACTION
    -0.07
     Assistance
    -0.07
    addChild
    -0.07
    뷁
    -0.07
    STIT
    -0.07
    ӣ
    -0.07
     são
    -0.06
     från
    -0.06
     variations
    -0.06
     Üniversitesi
    -0.06
    POSITIVE LOGITS
    🇬
    0.07
    حف
    0.07
    _poll
    0.07
    Ranked
    0.07
    _shot
    0.07
    꿍
    0.07
    vez
    0.06
    得意
    0.06
    .tel
    0.06
    揽
    0.06
    Act Density 0.008%

    No Known Activations