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

    Neuronpedia

    INDEX
    Explanations

    Random Sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elaide
    -0.07
    TouchUpInside
    -0.07
    Atoms
    -0.07
     Reasons
    -0.07
     occasions
    -0.07
    Er
    -0.07
    essenger
    -0.06
    RowIndex
    -0.06
     bagi
    -0.06
     alunos
    -0.06
    POSITIVE LOGITS
    河流
    0.08
    诫
    0.07
    人格
    0.07
    .Profile
    0.07
    菲
    0.07
     hạng
    0.07
    ダ
    0.07
    立方米
    0.07
    處理
    0.07
    平
    0.06
    Act Density 0.026%

    No Known Activations