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

    Neuronpedia

    INDEX
    Explanations

    connecting list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ketika
    0.39
    aları
    0.37
    İN
    0.35
    ৭
    0.35
    ib
    0.33
    ৬
    0.33
     to
    0.33
    ल
    0.32
    ৯
    0.32
    ↵
    0.31
    POSITIVE LOGITS
     not
    0.36
    مش
    0.33
    م
    0.32
     is
    0.32
    مون
    0.32
    ని
    0.32
    時候
    0.32
    0.31
     be
    0.30
    е
    0.30
    Act Density 0.823%

    No Known Activations