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

    Neuronpedia

    INDEX
    Explanations

    contract terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truck
    -0.07
    _detector
    -0.07
     covert
    -0.07
    廊
    -0.07
     kitchen
    -0.07
    XF
    -0.06
    <Void
    -0.06
     więc
    -0.06
     cage
    -0.06
     cắt
    -0.06
    POSITIVE LOGITS
    ',{↵
    0.06
    ROLE
    0.06
    WIN
    0.06
    OCKET
    0.06
    _SANITIZE
    0.06
    но
    0.06
    фров
    0.06
    물을
    0.06
     AMS
    0.06
    _DECL
    0.06
    Act Density 0.013%

    No Known Activations