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

    Neuronpedia

    INDEX
    Explanations

    after that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.51
    Quaternion
    0.51
    Sciences
    0.51
     Humanities
    0.50
     το
    0.49
     sonho
    0.48
     première
    0.47
     Accounting
    0.47
     Action
    0.47
     Bounds
    0.47
    POSITIVE LOGITS
    ed
    0.63
    اوی
    0.61
    evi
    0.57
    ون
    0.55
    ا
    0.55
    фт
    0.54
    e
    0.54
    もら
    0.52
    al
    0.52
    ીએ
    0.52
    Act Density 0.000%

    No Known Activations