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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     信
    -0.07
    letter
    -0.07
    Ư
    -0.07
    becca
    -0.07
    فر
    -0.07
     faculty
    -0.06
    国
    -0.06
    _YUV
    -0.06
     xxx
    -0.06
     distrust
    -0.06
    POSITIVE LOGITS
     داستان
    0.07
     clas
    0.06
     Ivory
    0.06
    콜걸
    0.06
    (clean
    0.06
    yonel
    0.06
    .Business
    0.06
     زنان
    0.06
     보고
    0.06
     Không
    0.06
    Act Density 0.983%

    No Known Activations