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

    Neuronpedia

    INDEX
    Explanations

    technical apparatus descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самов
    -0.07
     ()
↵
    -0.07
     ít
    -0.07
     ;
↵
↵
    -0.06
    aydı
    -0.06
     至
    -0.06
    efault
    -0.06
    .userdetails
    -0.06
     возможно
    -0.06
     дал
    -0.06
    POSITIVE LOGITS
     Escorts
    0.08
     dismissing
    0.06
     région
    0.06
    .nextToken
    0.06
    反应
    0.06
     ráno
    0.06
     sourceMapping
    0.06
     protested
    0.06
    $img
    0.05
    Cd
    0.05
    Act Density 0.116%

    No Known Activations