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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sponsors
    -0.07
     p
    -0.07
     Liebe
    -0.07
     Obs
    -0.07
     tea
    -0.07
     obrig
    -0.06
    modelName
    -0.06
    όρ
    -0.06
     структур
    -0.06
    .chapter
    -0.06
    POSITIVE LOGITS
     Siri
    0.06
    pData
    0.06
     hàng
    0.06
    chema
    0.06
    資料
    0.06
    怕
    0.06
     Ulus
    0.06
     평당
    0.06
     진
    0.05
    _Read
    0.05
    Act Density 0.017%

    No Known Activations