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

    Neuronpedia

    INDEX
    Explanations

    diagrams in scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forgetting
    -0.07
     paramName
    -0.06
    	el
    -0.06
    zh
    -0.06
    	expected
    -0.06
     Сем
    -0.06
    cgi
    -0.06
    -find
    -0.06
    .'</
    -0.06
     caffe
    -0.06
    POSITIVE LOGITS
    abolic
    0.07
     epid
    0.06
    /server
    0.06
    IF
    0.06
     DG
    0.06
    levant
    0.06
    .driver
    0.06
    <F
    0.06
     vinegar
    0.06
    /m
    0.06
    Act Density 0.017%

    No Known Activations