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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unfolds
    -0.07
    妍
    -0.06
    =str
    -0.06
     EOF
    -0.06
    >s
    -0.06
     الوق
    -0.06
    一瓶
    -0.06
     بش
    -0.06
    贯通
    -0.06
    宛
    -0.06
    POSITIVE LOGITS
    lease
    0.07
     MySqlCommand
    0.07
     Later
    0.07
    סיכום
    0.06
    ácil
    0.06
    🎱
    0.06
    .tel
    0.06
    .Criteria
    0.06
     Kiev
    0.06
    👸
    0.06
    Act Density 0.013%

    No Known Activations