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

    Neuronpedia

    INDEX
    Explanations

    doomsday predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Representatives
    -0.07
    .Timer
    -0.06
    یده
    -0.06
     resolutions
    -0.06
    StatusCode
    -0.06
    rolled
    -0.06
    _chain
    -0.06
    ک
    -0.06
    き
    -0.06
    chest
    -0.06
    POSITIVE LOGITS
    \'
    0.07
    ादन
    0.07
     thép
    0.07
    了一
    0.07
     canActivate
    0.06
     (...)
    0.06
     prag
    0.06
     grop
    0.06
     карти
    0.06
     شاهد
    0.06
    Act Density 0.045%

    No Known Activations