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

    Neuronpedia

    INDEX
    Explanations

    LLMs, NLP, CSF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuovamente
    0.41
     Cooler
    0.37
     VH
    0.37
     ২০
    0.36
     subarrays
    0.36
    mimeTypes
    0.36
     Sentencing
    0.36
     MLAs
    0.35
     ）
    0.35
     ().
    0.34
    POSITIVE LOGITS
    정보
    0.37
     वेळी
    0.35
     ሁሉም
    0.35
    Galer
    0.34
     قائمة
    0.34
     belonging
    0.33
    Bună
    0.33
     ਅਤੇ
    0.32
    Lem
    0.32
    ത്തിന്റെയും
    0.32
    Act Density 0.081%

    No Known Activations