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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devastating
    -0.08
     catastrophic
    -0.08
     विस
    -0.07
    .Word
    -0.07
    ட்ட
    -0.07
     শব্দ
    -0.07
    �
    -0.07
     constructs
    -0.07
     locus
    -0.07
     stitch
    -0.07
    POSITIVE LOGITS
     �
    0.10
    _IPV
    0.10
     maximale
    0.10
     máximo
    0.09
     ટકા
    0.09
     Максим
    0.09
     IPv
    0.09
     numerator
    0.09
    _HTTP
    0.09
    -max
    0.08
    Act Density 0.033%

    No Known Activations