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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이름
    -0.07
     speak
    -0.06
    ↵			↵
    -0.06
    .Get
    -0.06
     beet
    -0.06
     Lines
    -0.06
     Beet
    -0.06
    .sqlite
    -0.06
    adığ
    -0.06
     princip
    -0.06
    POSITIVE LOGITS
    (coord
    0.07
     relat
    0.06
    }%
    0.06
     그냥
    0.06
    orny
    0.06
    购买
    0.06
     Trav
    0.06
    .attach
    0.06
    '][$
    0.06
    _Total
    0.06
    Act Density 0.010%

    No Known Activations