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

    Neuronpedia

    INDEX
    Explanations

    start of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ные
    0.48
    nya
    0.47
    merksam
    0.44
     Übersicht
    0.44
    טית
    0.43
     বিত
    0.43
     نظامی
    0.42
    腖
    0.42
     NHT
    0.42
     těchto
    0.41
    POSITIVE LOGITS
    жди
    0.44
    ?}
    0.43
     {
    0.42
    !}
    0.41
    }
    0.41
    ნიშვნ
    0.41
     grossly
    0.40
     izgleda
    0.40
    }}{
    0.39
     anuv
    0.39
    Act Density 0.001%

    No Known Activations