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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vinc
    -0.07
    getOption
    -0.07
    acky
    -0.06
     seize
    -0.06
     ابو
    -0.06
    πί
    -0.06
    巡
    -0.06
    LEncoder
    -0.06
     zlep
    -0.06
     क
    -0.06
    POSITIVE LOGITS
    در
    0.07
    .isValid
    0.06
     disagreement
    0.06
     Fees
    0.06
     Rush
    0.06
    (output
    0.06
     cable
    0.06
    rum
    0.06
    rag
    0.06
    ={↵
    0.06
    Act Density 0.416%

    No Known Activations