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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     назад
    -0.06
     жит
    -0.06
    Representation
    -0.06
    Fl
    -0.06
    าหล
    -0.06
     {}".
    -0.06
    ournal
    -0.06
    .errorMessage
    -0.06
    вен
    -0.06
    Bounding
    -0.06
    POSITIVE LOGITS
    (cond
    0.07
    CLIENT
    0.07
    .getParent
    0.06
    words
    0.06
     intersects
    0.06
     {
↵
↵
↵
    0.06
     Fior
    0.06
     PAS
    0.06
    	word
    0.06
     zas
    0.06
    Act Density 0.002%

    No Known Activations