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

    Neuronpedia

    INDEX
    Explanations

    youtube watch links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ದಿ
    0.40
    ೨
    0.39
     HUM
    0.39
     रखती
    0.39
    .³
    0.39
     시민
    0.39
     แนะ
    0.38
    Citizens
    0.38
    DropdownBox
    0.38
     ხოლო
    0.38
    POSITIVE LOGITS
     format
    0.41
     content
    0.38
     wi
    0.36
    NR
    0.36
    content
    0.35
     कच्छ
    0.35
    #}
    0.35
    wi
    0.35
     TikTok
    0.34
     thérapeutique
    0.34
    Act Density 0.001%

    No Known Activations