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

    Neuronpedia

    INDEX
    Explanations

    identifiers, properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tar
    -0.07
    	len
    -0.07
    /at
    -0.07
    ponses
    -0.06
    aryl
    -0.06
     UIButton
    -0.06
     mít
    -0.06
    obs
    -0.06
     byt
    -0.06
    -return
    -0.06
    POSITIVE LOGITS
    Initialization
    0.06
    Liquid
    0.06
     Tolkien
    0.06
     supermarkets
    0.06
     Brisbane
    0.06
     추천
    0.06
    .**************
    0.06
    uels
    0.06
     composing
    0.06
     ads
    0.06
    Act Density 0.015%

    No Known Activations