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

    Neuronpedia

    INDEX
    Explanations

    analysis of disallowed content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alog
    -0.08
     조금
    -0.08
    onneur
    -0.08
    (T
    -0.08
    лот
    -0.08
     gracias
    -0.07
     grazie
    -0.07
     sinu
    -0.07
    칼
    -0.07
     twg
    -0.07
    POSITIVE LOGITS
     sandbox
    0.10
    .so
    0.09
     unsus
    0.09
    .sock
    0.09
     beveilig
    0.08
     zabez
    0.08
     নিরাপ
    0.08
     victime
    0.08
     सुरक्षित
    0.08
     voluntary
    0.08
    Act Density 0.023%

    No Known Activations