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

    Neuronpedia

    INDEX
    Explanations

    Figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пласти
    -0.07
     nuovo
    -0.06
    FFF
    -0.06
     priest
    -0.06
     heuristic
    -0.06
    editar
    -0.06
     Hubb
    -0.06
     Cedar
    -0.06
    　　 　
    -0.06
    ulner
    -0.06
    POSITIVE LOGITS
    =pos
    0.06
     epis
    0.06
    (qu
    0.06
     náklady
    0.06
    499
    0.06
    _DIM
    0.06
    ablytyped
    0.05
    ultan
    0.05
    $post
    0.05
    ‌پدیای
    0.05
    Act Density 0.004%

    No Known Activations