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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']↵↵↵
    -0.08
     も
    -0.07
     νεφοκάλυψης
    -0.07
     incorporates
    -0.07
    	Function
    -0.07
    =log
    -0.07
     ]}↵
    -0.06
    _elt
    -0.06
    ↵      ↵
    -0.06
    private
    -0.06
    POSITIVE LOGITS
    rip
    0.07
     Hyper
    0.06
     mushrooms
    0.06
     demok
    0.06
    ималь
    0.06
     Ange
    0.06
     ipt
    0.06
    olynomial
    0.06
     unhappy
    0.06
    Gi
    0.06
    Act Density 0.000%

    No Known Activations