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

    Neuronpedia

    INDEX
    Explanations

    Israeli-Palestinian conflict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    δ
    -0.09
    明年
    -0.07
     günümüz
    -0.07
     λ
    -0.07
    竽
    -0.07
    �除
    -0.06
    Wy
    -0.06
    Kin
    -0.06
    .kind
    -0.06
    itionally
    -0.06
    POSITIVE LOGITS
     flutter
    0.08
    期刊
    0.08
     rake
    0.08
    טי
    0.07
     Flying
    0.07
    巴拉
    0.07
    strategy
    0.07
    utf
    0.07
     adorable
    0.07
    арь
    0.07
    Act Density 0.044%

    No Known Activations