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

    Neuronpedia

    INDEX
    Explanations

    where which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intrinsic
    -0.07
    ederal
    -0.06
     _{
    -0.06
     refr
    -0.06
    REF
    -0.06
     expensive
    -0.06
    SPORT
    -0.06
     expenditures
    -0.06
     physique
    -0.06
    573
    -0.06
    POSITIVE LOGITS
     where
    0.11
     Dash
    0.08
    접
    0.07
     όπου
    0.07
    .userInfo
    0.07
     jejich
    0.07
     Packers
    0.07
    onne
    0.07
     Catherine
    0.06
    htmlspecialchars
    0.06
    Act Density 0.048%

    No Known Activations