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

    Neuronpedia

    INDEX
    Explanations

    permit, director, APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ma
    0.42
    zyst
    0.40
    gyro
    0.40
    jährigen
    0.40
    zd
    0.40
    anch
    0.39
    ailand
    0.39
    TextBlock
    0.39
     વર્ષ
    0.39
    HighScore
    0.39
    POSITIVE LOGITS
     svol
    0.45
    अन्य
    0.44
     ainsi
    0.43
     vaksin
    0.43
     precum
    0.43
    再現
    0.43
     اشاره
    0.43
     digunakan
    0.42
     yang
    0.42
     whom
    0.42
    Act Density 0.001%

    No Known Activations