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

    Neuronpedia

    INDEX
    Explanations

    ASP.NET code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     artifact
    -0.07
     cultures
    -0.07
    pm
    -0.07
     pure
    -0.07
    .Change
    -0.07
     harder
    -0.06
     directive
    -0.06
    “If
    -0.06
    README
    -0.06
     upper
    -0.06
    POSITIVE LOGITS
    sehen
    0.06
    ,pos
    0.06
    ั
    0.06
     بايد
    0.06
     Sudoku
    0.06
     aş
    0.06
    搜
    0.06
    -founder
    0.06
    croft
    0.06
    bur
    0.06
    Act Density 0.018%

    No Known Activations