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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    久
    -0.08
    Sans
    -0.08
    vec
    -0.07
     дорог
    -0.07
    align
    -0.07
     huge
    -0.07
     contradiction
    -0.07
     Become
    -0.07
     Alumni
    -0.07
    dex
    -0.07
    POSITIVE LOGITS
    鲾
    0.08
    管理制度
    0.07
    쉴
    0.07
    ᶻ
    0.07
     murdered
    0.07
     procedures
    0.07
    .setPositiveButton
    0.07
    🅾
    0.07
    _kategori
    0.07
    烻
    0.07
    Act Density 0.000%

    No Known Activations