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
    Feed
    -0.08
     alpha
    -0.07
    ickness
    -0.07
     Init
    -0.07
    initial
    -0.07
    (zip
    -0.07
    	else
    -0.06
     Paste
    -0.06
    represented
    -0.06
     Lent
    -0.06
    POSITIVE LOGITS
    317
    0.07
     चलत
    0.07
     acompanh
    0.06
    авлива
    0.06
     prin
    0.06
     Coverage
    0.06
     Север
    0.06
     prvním
    0.06
     Friday
    0.06
     cinsel
    0.06
    Act Density 0.181%

    No Known Activations