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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xOffset
    -0.07
    .Π
    -0.07
     무
    -0.07
    不要
    -0.06
     contato
    -0.06
     stop
    -0.06
     �
    -0.06
    itori
    -0.06
     Gaut
    -0.06
     cultivation
    -0.06
    POSITIVE LOGITS
     references
    0.07
     сер
    0.06
     컨
    0.06
    Toggle
    0.06
    HostException
    0.06
     "<?
    0.06
     //'
    0.06
     Birleşik
    0.06
    utex
    0.06
     bien
    0.06
    Act Density 0.060%

    No Known Activations