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

    Neuronpedia

    INDEX
    Explanations

    Grids and Meshes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revisions
    -0.08
     Россий
    -0.07
    	Il
    -0.07
     insurance
    -0.07
     systemic
    -0.07
    详情
    -0.06
    代理
    -0.06
    引っ
    -0.06
    ,/
    -0.06
    -unstyled
    -0.06
    POSITIVE LOGITS
    ᨲ
    0.07
    .after
    0.06
    إبراهيم
    0.06
     שהיא
    0.06
    amaño
    0.06
     drei
    0.06
    ViewSet
    0.06
     Thief
    0.06
    垡
    0.06
    ﮩ
    0.06
    Act Density 0.059%

    No Known Activations