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

    Neuronpedia

    INDEX
    Explanations

    logic puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尾
    -0.07
     schö
    -0.07
     Porn
    -0.06
     maintaining
    -0.06
    -Day
    -0.06
     اختی
    -0.06
    東
    -0.06
     unordered
    -0.06
     krij
    -0.06
     hip
    -0.06
    POSITIVE LOGITS
    embre
    0.07
    _location
    0.06
    691
    0.06
     tho
    0.06
    Court
    0.06
    download
    0.06
    \'
    0.06
    нг
    0.06
     dismissing
    0.06
    OURSE
    0.05
    Act Density 0.006%

    No Known Activations