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

    Neuronpedia

    INDEX
    Explanations

    My

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Benedict
    -0.08
    図
    -0.06
    Hop
    -0.06
    prefix
    -0.06
     Rodr
    -0.06
     कप
    -0.06
     张
    -0.06
     Calvin
    -0.06
    Response
    -0.06
    ويل
    -0.06
    POSITIVE LOGITS
    webtoken
    0.06
     było
    0.06
     stylish
    0.06
     сч
    0.06
    $array
    0.06
     griev
    0.06
     IICIII
    0.06
    ΕΥ
    0.06
    +xml
    0.06
    cl
    0.06
    Act Density 0.046%

    No Known Activations