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

    Neuronpedia

    INDEX
    Explanations

    import statements with from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YS
    1.15
    eta
    1.14
    টিআই
    1.12
    ξ
    1.10
    NDE
    1.09
    ier
    1.09
    LH
    1.08
    ⃞
    1.08
    鵑
    1.07
    RAY
    1.05
    POSITIVE LOGITS
    ת
    1.29
    ف
    1.27
    те
    1.16
    го
    1.12
    stens
    1.08
    4
    1.05
     ১০
    1.03
    кон
    1.02
     wasteland
    1.01
    3
    1.01
    Act Density 0.019%

    No Known Activations