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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᨳ
    -0.07
    路况
    -0.07
    -prom
    -0.07
    理论上
    -0.07
     треб
    -0.07
    =test
    -0.07
    +</
    -0.07
    诚
    -0.07
     rebell
    -0.06
    -tech
    -0.06
    POSITIVE LOGITS
     Pel
    0.08
    ɗ
    0.07
     seating
    0.07
    acterial
    0.07
    	synchronized
    0.07
    0.07
    גן
    0.07
    鏊
    0.07
     Nat
    0.07
     sling
    0.07
    Act Density 0.049%

    No Known Activations