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

    Neuronpedia

    INDEX
    Explanations

    say "st"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �ng
    -0.07
     &&↵
    -0.06
    kee
    -0.06
     warns
    -0.06
    zan
    -0.06
    _levels
    -0.06
    ruh
    -0.06
    ención
    -0.06
     +-
    -0.06
    除了
    -0.06
    POSITIVE LOGITS
    нием
    0.07
    oso
    0.07
    (enemy
    0.07
    APPER
    0.07
    кого
    0.06
    Shapes
    0.06
    appable
    0.06
    arter
    0.06
    askan
    0.06
    กลาง
    0.06
    Act Density 0.091%

    No Known Activations