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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    来了
    -0.06
     До
    -0.06
    Device
    -0.06
     ich
    -0.06
    _RANDOM
    -0.06
     succes
    -0.06
     nějaký
    -0.06
    克
    -0.06
    инки
    -0.06
    Timestamp
    -0.06
    POSITIVE LOGITS
    itle
    0.07
    ۳۶
    0.07
     blazing
    0.06
    esthetic
    0.06
     nbytes
    0.06
     süre
    0.06
    aket
    0.06
     continuum
    0.06
     orderby
    0.06
    .hour
    0.06
    Act Density 0.218%

    No Known Activations