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

    Neuronpedia

    INDEX
    Explanations

    unfathomable changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zeal
    0.45
    दाबाद
    0.42
    ಧ
    0.41
    ඓ
    0.39
     ارد
    0.38
     ассо
    0.37
     burdens
    0.36
    ච්
    0.36
    োগান
    0.35
     Ueda
    0.35
    POSITIVE LOGITS
     Sof
    0.44
    astrar
    0.39
     chuyển
    0.39
     AMP
    0.39
     enough
    0.39
     Esa
    0.38
     عد
    0.37
     방법에
    0.37
     Wit
    0.37
     מפ
    0.37
    Act Density 0.007%

    No Known Activations