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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aide
    -0.07
     매
    -0.07
     Male
    -0.07
     male
    -0.07
     animals
    -0.06
     бес
    -0.06
    uracy
    -0.06
     Glory
    -0.06
    -support
    -0.06
    ฝ
    -0.06
    POSITIVE LOGITS
     مدیریت
    0.07
     suf
    0.07
     �
    0.06
     vf
    0.06
    .iter
    0.06
    reply
    0.06
    -proof
    0.06
    _TEM
    0.06
    オリ
    0.06
     ـ
    0.06
    Act Density 0.093%

    No Known Activations