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

    Neuronpedia

    INDEX
    Explanations

    code/technical strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caves
    -0.07
     attached
    -0.07
    ACION
    -0.06
     duplicates
    -0.06
    [element
    -0.06
     sheep
    -0.06
    ین
    -0.06
    ariance
    -0.06
     Blues
    -0.06
    ف
    -0.06
    POSITIVE LOGITS
    “,
    0.07
    MethodImpl
    0.06
    _EXPR
    0.06
    .／
    0.06
     Druid
    0.06
     ***!↵
    0.06
    "<
    0.06
    中华
    0.06
    fos
    0.06
    _CAR
    0.06
    Act Density 0.002%

    No Known Activations