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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     badge
    -0.07
    _reaction
    -0.07
     пош
    -0.07
    	parameters
    -0.07
    耗
    -0.07
     legality
    -0.06
    etypes
    -0.06
    classification
    -0.06
     Wert
    -0.06
    정을
    -0.06
    POSITIVE LOGITS
     nek
    0.06
     pol
    0.06
     voor
    0.06
    .SetActive
    0.06
     Pemb
    0.06
    �
    0.06
    .spec
    0.06
     avril
    0.06
     spring
    0.06
     Indy
    0.06
    Act Density 0.001%

    No Known Activations