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

    Neuronpedia

    INDEX
    Explanations

    high degree of intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Telangana
    0.63
     Бүгенге
    0.61
     Ztg
    0.60
     Öğ
    0.59
    ವೇಂದ್ರ
    0.57
     Học
    0.56
     Onun
    0.55
     Commencez
    0.55
     Jeśli
    0.54
     Màu
    0.53
    POSITIVE LOGITS
    .
    0.69
    h
    0.68
    f
    0.67
    us
    0.66
     l
    0.63
    j
    0.63
    ine
    0.63
    ang
    0.63
    v
    0.61
    ue
    0.58
    Act Density 0.576%

    No Known Activations