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

    Neuronpedia

    INDEX
    Explanations

    conversational variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。”
    0.34
     stylistic
    0.33
     blur
    0.32
    上
    0.32
     thumbnail
    0.31
     하나의
    0.31
     zumindest
    0.31
    。」
    0.30
     oa
    0.30
    ，
    0.30
    POSITIVE LOGITS
    ilyn
    0.29
     Airlines
    0.28
    kaa
    0.28
     merhabalar
    0.28
     Entertainment
    0.28
    mandu
    0.28
     এলাম
    0.28
    ’
    0.27
    ạm
    0.27
    fam
    0.27
    Act Density 0.008%

    No Known Activations