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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PTY
    -0.07
    ardin
    -0.06
     harms
    -0.06
     Lau
    -0.06
    몬
    -0.06
    amic
    -0.06
     Σύ
    -0.06
     цель
    -0.06
    ตำบล
    -0.06
     florida
    -0.06
    POSITIVE LOGITS
    property
    0.06
     本
    0.06
    거리
    0.06
     Blick
    0.06
     pra
    0.06
     International
    0.06
    ynı
    0.06
    /↵↵
    0.06
    erde
    0.06
    ै.
    0.06
    Act Density 0.000%

    No Known Activations