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

    Neuronpedia

    INDEX
    Explanations

    Roman Empire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pissed
    0.51
     Raptor
    0.48
     arbe
    0.47
     genero
    0.47
     mesmerizing
    0.46
     jerk
    0.45
    нг
    0.45
    <0xF4>
    0.44
     JN
    0.44
    ៀង
    0.44
    POSITIVE LOGITS
    ת
    0.63
    い
    0.61
    ла
    0.58
    т
    0.53
    اع
    0.50
    み
    0.49
    acji
    0.49
    री
    0.49
    ,|
    0.49
    ब
    0.49
    Act Density 0.000%

    No Known Activations