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

    Neuronpedia

    INDEX
    Explanations

    repo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ITH
    -0.08
    .Paint
    -0.07
    SION
    -0.06
    ISR
    -0.06
    "M
    -0.06
    pdata
    -0.06
    _orders
    -0.06
    ン
    -0.06
     Bulldogs
    -0.06
     guilt
    -0.06
    POSITIVE LOGITS
     Оп
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    Α
    0.07
     Colorado
    0.07
     обс
    0.06
    Te
    0.06
    Colorado
    0.06
     inbox
    0.06
     arcpy
    0.06
     lã
    0.06
    Act Density 0.003%

    No Known Activations