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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     き
    -0.07
     」
    -0.07
     디
    -0.07
    Heroes
    -0.06
     Axios
    -0.06
     selfish
    -0.06
     や
    -0.06
    .xy
    -0.06
    .dense
    -0.06
    ...)
    -0.06
    POSITIVE LOGITS
    فصل
    0.06
    xit
    0.06
    sembl
    0.06
    .appspot
    0.06
     quit
    0.06
     khỏ
    0.06
    -N
    0.06
    (Program
    0.06
    Intialized
    0.06
    �
    0.06
    Act Density 0.111%

    No Known Activations