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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䗖
    -0.08
    	sound
    -0.07
     addCriterion
    -0.07
    情况进行
    -0.07
     indemn
    -0.07
     auditing
    -0.07
    	dist
    -0.06
    性强
    -0.06
    该怎么
    -0.06
     pewnością
    -0.06
    POSITIVE LOGITS
     ('
    0.07
    Words
    0.07
     ک
    0.07
    .W
    0.07
    槍
    0.07
     France
    0.07
     LoginComponent
    0.07
    電話
    0.07
     English
    0.06
     prosecutors
    0.06
    Act Density 0.006%

    No Known Activations