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

    Neuronpedia

    INDEX
    Explanations

    ===========

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kil
    -0.08
     alc
    -0.07
     concerned
    -0.07
     dici
    -0.07
     Set
    -0.07
    -meter
    -0.07
     גם
    -0.07
    挈
    -0.07
    (q
    -0.07
     Cry
    -0.07
    POSITIVE LOGITS
    hasil
    0.07
    想过
    0.07
    oops
    0.07
     :::
    0.07
    쓩
    0.07
     שלך
    0.07
    🤣
    0.07
    formData
    0.07
     humiliation
    0.06
    ностей
    0.06
    Act Density 0.003%

    No Known Activations