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

    Neuronpedia

    INDEX
    Explanations

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оя
    -0.06
    $action
    -0.06
    .Gradient
    -0.06
     blat
    -0.06
    _challenge
    -0.06
    Пос
    -0.06
    'nun
    -0.06
     sac
    -0.06
    GORITH
    -0.06
    '>$
    -0.06
    POSITIVE LOGITS
     kindly
    0.10
    抽
    0.07
     charitable
    0.07
     Yuan
    0.07
     rif
    0.07
    Enabled
    0.07
    隆
    0.07
     관련
    0.06
    人が
    0.06
    .Script
    0.06
    Act Density 0.010%

    No Known Activations