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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Playable
    -0.07
    Returns
    -0.07
    %");↵
    -0.06
    ecimal
    -0.06
    rtype
    -0.06
    .INT
    -0.06
    Ό
    -0.06
    aterno
    -0.06
    .";
↵
    -0.06
    bitrary
    -0.06
    POSITIVE LOGITS
     artistic
    0.07
    ließ
    0.07
    /small
    0.07
     modulation
    0.07
    .stock
    0.07
     organism
    0.07
     Whole
    0.06
    ких
    0.06
     Agile
    0.06
     大阪
    0.06
    Act Density 0.006%

    No Known Activations