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

    Neuronpedia

    INDEX
    Explanations

    code and logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commentary
    -0.06
     ری
    -0.06
     cessation
    -0.06
    owl
    -0.06
    _PHONE
    -0.06
     　　 　
    -0.06
     enraged
    -0.06
     aden
    -0.06
    ovali
    -0.06
    reachable
    -0.06
    POSITIVE LOGITS
    Emily
    0.06
    iliated
    0.06
     reluctantly
    0.06
    جميع
    0.06
    484
    0.06
    emit
    0.06
     forwarded
    0.06
     stimulated
    0.06
    لسل
    0.06
    .setBorder
    0.06
    Act Density 0.042%

    No Known Activations