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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itsu
    -0.07
    vt
    -0.07
    まさ
    -0.07
    ét
    -0.07
     cycling
    -0.07
    bal
    -0.07
    elsen
    -0.07
    .Warning
    -0.07
     wrestler
    -0.07
    hetto
    -0.06
    POSITIVE LOGITS
    '].
    0.07
    eax
    0.07
    真皮
    0.07
    と思う
    0.07
    jpeg
    0.07
     "'"
    0.06
    UED
    0.06
    얾
    0.06
    .references
    0.06
     Continued
    0.06
    Act Density 0.002%

    No Known Activations