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

    Neuronpedia

    INDEX
    Explanations

    words and numbers mixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    甘
    0.37
     संश्लेषण
    0.37
     ob
    0.36
    이블
    0.36
     shrank
    0.35
    gement
    0.35
     kise
    0.35
    恣
    0.35
    ρθ
    0.34
     actif
    0.34
    POSITIVE LOGITS
    Читати
    0.45
     READ
    0.45
     Estimated
    0.44
    Estimated
    0.43
     read
    0.38
     Read
    0.38
     чита
    0.38
     Continue
    0.36
    Читать
    0.35
    াহা
    0.35
    Act Density 0.001%

    No Known Activations