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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    推
    -0.08
    	Size
    -0.08
     �
    -0.07
     Dip
    -0.07
     vicious
    -0.06
    310
    -0.06
    ums
    -0.06
     Forums
    -0.06
     Waist
    -0.06
     Ont
    -0.06
    POSITIVE LOGITS
    और
    0.07
    forma
    0.07
     soát
    0.07
    ailable
    0.06
     legitimate
    0.06
    ()<<
    0.06
     synthes
    0.06
    alleries
    0.06
    Snippet
    0.06
    -stack
    0.06
    Act Density 0.011%

    No Known Activations