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

    Neuronpedia

    INDEX
    Explanations

    from/in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Німеч
    -0.07
     посад
    -0.07
     Afterwards
    -0.07
     Dane
    -0.07
    DCF
    -0.07
    boolean
    -0.07
     gå
    -0.07
     reachable
    -0.06
    	dist
    -0.06
    $product
    -0.06
    POSITIVE LOGITS
     institutional
    0.07
     vyu
    0.07
    TEMPL
    0.06
    _SSL
    0.06
     حسین
    0.06
    unteers
    0.06
    fusion
    0.06
    _EXTERN
    0.06
    roups
    0.06
    宅
    0.06
    Act Density 0.074%

    No Known Activations