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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doctor
    -0.07
    ሺ
    -0.07
     Pamela
    -0.07
     perennial
    -0.07
     LaTeX
    -0.07
     sns
    -0.07
     saja
    -0.07
     Doctor
    -0.07
     désormais
    -0.06
     flourish
    -0.06
    POSITIVE LOGITS
    �
    0.08
    债
    0.07
    英镑
    0.07
    忒
    0.06
    海淀
    0.06
    机
    0.06
    ChildIndex
    0.06
    burg
    0.06
    거리
    0.06
    ᠴ
    0.06
    Act Density 0.000%

    No Known Activations