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

    Neuronpedia

    INDEX
    Explanations

    tokens before numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.94
    e
    0.85
    human
    0.83
     the
    0.77
    ce
    0.76
    a
    0.75
    Entrepreneur
    0.75
    Introduction
    0.72
    th
    0.71
     DIFFIC
    0.70
    POSITIVE LOGITS
    wijl
    0.85
     данные
    0.83
     duomen
    0.82
     отобра
    0.80
     natthi
    0.79
     cbind
    0.79
    合せ
    0.79
     umfasst
    0.78
     tathapi
    0.78
     koost
    0.77
    Act Density 0.000%

    No Known Activations