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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _send
    -0.07
    忍不住
    -0.07
    gnore
    -0.07
     Revel
    -0.06
    ฏ
    -0.06
     Vinyl
    -0.06
     Blood
    -0.06
    _dd
    -0.06
    并没有
    -0.06
     Penny
    -0.06
    POSITIVE LOGITS
     weighting
    0.07
    abouts
    0.07
    ografía
    0.07
     żyw
    0.07
    مواق
    0.06
    يقة
    0.06
    ographic
    0.06
     özelli
    0.06
    itsu
    0.06
    튕
    0.06
    Act Density 0.001%

    No Known Activations