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

    Neuronpedia

    INDEX
    Explanations

    figures and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agak
    0.53
     końca
    0.51
    ्ड
    0.50
     uğ
    0.49
     tingkat
    0.48
     quả
    0.48
     tenere
    0.48
     gradation
    0.47
     stylesheet
    0.47
    蜍
    0.47
    POSITIVE LOGITS
    Р
    0.53
    ^{+}
    0.48
    s
    0.47
    ر
    0.45
    sockets
    0.45
    northern
    0.42
     DEALINGS
    0.41
    ה
    0.40
    وت
    0.40
    δ
    0.40
    Act Density 0.335%

    No Known Activations