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

    Neuronpedia

    INDEX
    Explanations

    dates and BCE eras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Representatives
    0.48
    যদিও
    0.46
    Б
    0.46
     !\
    0.45
    Initi
    0.45
     проце
    0.44
    ।-
    0.43
    せた
    0.43
    И
    0.43
    졌
    0.42
    POSITIVE LOGITS
    hattan
    0.52
     Hiram
    0.45
     ચો
    0.43
     decay
    0.42
    ulos
    0.42
    ing
    0.42
    érer
    0.42
     grammat
    0.41
    taire
    0.41
     మూ
    0.41
    Act Density 0.003%

    No Known Activations