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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tela
    0.35
    λιο
    0.33
    ́p
    0.33
    िम
    0.32
    tope
    0.32
    YM
    0.31
    occupied
    0.31
    yata
    0.31
    Uninstall
    0.30
    ዖ
    0.30
    POSITIVE LOGITS
    ️
    0.40
     gotta
    0.32
    \)
    0.31
    %)
    0.30
    मिटेड
    0.29
     magnificent
    0.29
     excruciating
    0.29
     hotspots
    0.29
     आल्सो
    0.29
    withstanding
    0.28
    Act Density 0.593%

    No Known Activations