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

    Neuronpedia

    INDEX
    Explanations

    verification, comments, example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocyanate
    0.50
    owanych
    0.48
    axal
    0.47
     MS
    0.47
    recation
    0.44
     баш
    0.44
    UND
    0.43
    URCH
    0.43
     OSA
    0.43
    ifi
    0.43
    POSITIVE LOGITS
    비
    0.51
     indivíduos
    0.49
    مان
    0.49
     establecimiento
    0.47
     água
    0.47
    idelijk
    0.46
    ៊ី
    0.46
     الماء
    0.45
    ኋላ
    0.45
    有一定的
    0.45
    Act Density 0.000%

    No Known Activations