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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sz
    -0.07
    okie
    -0.06
     inne
    -0.06
     vede
    -0.06
     puppy
    -0.06
    üle
    -0.06
    codile
    -0.06
    ();
↵
    -0.06
    istry
    -0.06
    porno
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .redirect
    0.07
     waypoint
    0.07
     аж
    0.07
     مان
    0.07
     MONTH
    0.06
    :])↵
    0.06
     زم
    0.06
    month
    0.06
     ----------------------------------------------------------------------------
    0.06
    Act Density 0.001%

    No Known Activations