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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sales
    -0.67
    ales
    -0.66
     tiny
    -0.62
     existed
    -0.62
    клопе
    -0.59
    ped
    -0.58
    ez
    -0.56
    timer
    -0.56
     timers
    -0.55
     BoxFit
    -0.55
    POSITIVE LOGITS
    TypedDataSet
    0.67
     raiſ
    0.60
     بيها
    0.58
     Проци
    0.56
    Traceback
    0.56
     Melhor
    0.54
     abſ
    0.54
     myſelf
    0.54
    grafías
    0.53
    bleau
    0.53
    Act Density 0.411%

    No Known Activations