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

    Neuronpedia

    INDEX
    Explanations

    lists or numbered items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icherung
    0.44
     nenhum
    0.43
     attempted
    0.42
    Von
    0.41
     sehe
    0.40
    ف
    0.40
    '
    0.39
    』（
    0.39
     issue
    0.39
     puedo
    0.39
    POSITIVE LOGITS
    โ
    0.57
    โลก
    0.51
    IENTS
    0.50
    ूड
    0.50
     데이터
    0.50
    ເຮັດ
    0.49
    െടു
    0.48
    ]।
    0.48
     கிலோ
    0.47
     문자
    0.46
    Act Density 0.000%

    No Known Activations