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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     có
    -0.07
    ische
    -0.06
    .Model
    -0.06
    .Repository
    -0.06
     ],↵↵
    -0.06
    NewUrlParser
    -0.06
     thận
    -0.06
     Dương
    -0.06
     международ
    -0.06
    	transform
    -0.06
    POSITIVE LOGITS
    /org
    0.08
    _LO
    0.07
     अत
    0.07
    richt
    0.06
     Mostly
    0.06
     Saga
    0.06
     лим
    0.06
     مرد
    0.06
    emonic
    0.06
     ört
    0.06
    Act Density 0.002%

    No Known Activations