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

    Neuronpedia

    INDEX
    Explanations

    greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lena
    0.43
    $_{
    0.41
    iena
    0.41
    aila
    0.39
    uric
    0.38
    starch
    0.38
    iscale
    0.37
    umi
    0.37
    ieni
    0.36
    ul
    0.36
    POSITIVE LOGITS
    嗯
    0.39
    Business
    0.38
     शब्द
    0.37
     zá
    0.37
     başlat
    0.37
    अपना
    0.37
    ेंटिस
    0.37
     destino
    0.36
     서비스
    0.36
    وعه
    0.35
    Act Density 0.098%

    No Known Activations