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

    Neuronpedia

    INDEX
    Explanations

    Formal/informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     husband
    -0.07
     boiled
    -0.06
     우
    -0.06
     scp
    -0.06
    killer
    -0.06
     yaptığ
    -0.06
    세
    -0.06
     начина
    -0.06
    mlx
    -0.06
     chor
    -0.06
    POSITIVE LOGITS
    $array
    0.07
    返回
    0.07
    owns
    0.06
    ideo
    0.06
     Wrapped
    0.06
     Rest
    0.06
    atives
    0.06
     شر
    0.06
    fed
    0.06
     Requirements
    0.06
    Act Density 0.044%

    No Known Activations