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

    Neuronpedia

    INDEX
    Explanations

    element positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �州
    -0.07
    업체
    -0.06
     Amendment
    -0.06
    Slide
    -0.06
    iele
    -0.06
    馬
    -0.06
     step
    -0.06
     мире
    -0.06
    Z
    -0.06
    vana
    -0.06
    POSITIVE LOGITS
     endure
    0.07
     sebuah
    0.06
    _PP
    0.06
    ibli
    0.06
     TB
    0.06
    -shell
    0.06
    .Ex
    0.06
    ;↵↵↵↵↵
    0.06
    licit
    0.06
     Fig
    0.06
    Act Density 0.054%

    No Known Activations