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

    Neuronpedia

    INDEX
    Explanations

    throwing motion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ร์
    0.36
    क्रो
    0.34
    شون
    0.34
     involution
    0.33
    ]")]
    0.33
    িল্প
    0.33
    BLACKLIST
    0.32
    Compression
    0.32
     subsum
    0.32
    Methoxy
    0.31
    POSITIVE LOGITS
    read
    0.36
     Read
    0.36
    je
    0.35
    more
    0.33
     Baca
    0.33
     Umm
    0.32
    Read
    0.32
     READ
    0.32
    politics
    0.32
    posts
    0.31
    Act Density 0.001%

    No Known Activations