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

    Neuronpedia

    INDEX
    Explanations

    hundreds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drinking
    -0.83
     Drinking
    -0.77
     Hundreds
    -0.77
     hundred
    -0.70
    Hundreds
    -0.70
    drinking
    -0.69
    MLLoader
    -0.68
    hundred
    -0.67
    Drinking
    -0.67
     للاسماء
    -0.66
    POSITIVE LOGITS
    TestingModule
    0.53
    CppCodeGen
    0.52
     pseud
    0.51
     autorytatywna
    0.49
    phin
    0.47
     kaynağından
    0.47
    MIDDLEWARE
    0.46
    siębior
    0.46
     driver
    0.45
    acity
    0.45
    Act Density 0.098%

    No Known Activations