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

    Neuronpedia

    INDEX
    Explanations

    controlled trials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     змін
    0.67
     sửa
    0.66
     slučaju
    0.66
     словарь
    0.65
     договору
    0.65
     музыку
    0.64
     слово
    0.64
    :
    0.64
    ção
    0.63
    ምት
    0.63
    POSITIVE LOGITS
    İ
    0.69
    і
    0.63
    OU
    0.60
    AVE
    0.59
    ק
    0.56
    ISH
    0.55
     JI
    0.55
     Stanley
    0.53
    İN
    0.53
    ייש
    0.52
    Act Density 0.002%

    No Known Activations