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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الكريم
    -0.08
    forderungen
    -0.07
     увер
    -0.07
     evt
    -0.07
    Inherited
    -0.07
    urd
    -0.07
     flink
    -0.07
    	   ↵
    -0.07
    ób
    -0.07
     مبلغ
    -0.07
    POSITIVE LOGITS
     implications
    0.12
    意义
    0.11
     смысл
    0.10
     consequences
    0.10
     repercussions
    0.10
     origins
    0.10
     significance
    0.09
    作用
    0.09
     drawbacks
    0.09
     BEEN
    0.09
    Act Density 0.150%

    No Known Activations