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

    Neuronpedia

    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mại
    -0.09
    愫
    -0.08
    -founder
    -0.07
    _IMPORTED
    -0.07
    iciary
    -0.07
    ˬ
    -0.07
    精神文明
    -0.07
    שמר
    -0.07
    /env
    -0.07
     Styles
    -0.07
    POSITIVE LOGITS
     attacking
    0.08
    pleasant
    0.07
    لقب
    0.07
    -filter
    0.07
    预计
    0.07
    _ipc
    0.07
     대하여
    0.07
    亶
    0.07
     başka
    0.07
     dop
    0.07
    Act Density 0.002%

    No Known Activations