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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ultra
    -0.07
     teng
    -0.06
    ilton
    -0.06
    _BGR
    -0.06
    Birthday
    -0.06
    ='',↵
    -0.06
    /audio
    -0.06
    Japan
    -0.06
    Cargo
    -0.06
     обязан
    -0.06
    POSITIVE LOGITS
     člen
    0.07
     улуч
    0.06
     brings
    0.06
     Население
    0.06
     Aph
    0.06
    ices
    0.06
     srand
    0.06
    OLUMNS
    0.06
     nginx
    0.06
     요구
    0.06
    Act Density 0.010%

    No Known Activations