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

    Neuronpedia

    INDEX
    Explanations

    Evaluate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prob
    -0.07
     اذا
    -0.07
    但是我
    -0.06
    Ӏ
    -0.06
    都很
    -0.06
    /api
    -0.06
    /up
    -0.06
    ilibrium
    -0.06
    verse
    -0.06
    灵敏
    -0.06
    POSITIVE LOGITS
    _fwd
    0.07
     husbands
    0.07
    média
    0.07
    的缘
    0.07
    ...");
↵
    0.07
    몇
    0.07
    撑
    0.07
    -Clause
    0.07
    UPPORTED
    0.06
    edReader
    0.06
    Act Density 0.113%

    No Known Activations