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

    Neuronpedia

    INDEX
    Explanations

    ci

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paths
    -0.07
    ענה
    -0.07
    .getPlayer
    -0.07
     threaten
    -0.07
    湲
    -0.07
    䨰
    -0.07
    	describe
    -0.07
    软雅黑
    -0.07
     Chern
    -0.07
     Vish
    -0.06
    POSITIVE LOGITS
    Deleting
    0.08
    _o
    0.08
     bezpieczeńst
    0.07
    (o
    0.07
     nominate
    0.07
     пере
    0.07
    Got
    0.07
    _n
    0.07
    _loc
    0.07
    _gt
    0.07
    Act Density 0.015%

    No Known Activations