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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chiefly
    -0.07
    jis
    -0.07
     ili
    -0.07
     preparations
    -0.07
     AH
    -0.06
    distance
    -0.06
     lux
    -0.06
    urations
    -0.06
    -fat
    -0.06
     prelim
    -0.06
    POSITIVE LOGITS
    Canceled
    0.06
    Opera
    0.06
    .peer
    0.06
     دکتر
    0.06
     Gothic
    0.06
    [port
    0.06
     Joker
    0.06
    Danger
    0.06
    ogn
    0.06
     Jade
    0.06
    Act Density 0.026%

    No Known Activations