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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Govern
    -0.07
     سرو
    -0.06
    FontOfSize
    -0.06
    巡
    -0.06
    defer
    -0.06
    Ệ
    -0.06
     XSS
    -0.06
    burse
    -0.06
    istro
    -0.06
    case
    -0.06
    POSITIVE LOGITS
     đội
    0.07
    .Z
    0.07
     t
    0.07
    (forms
    0.07
    Existing
    0.06
    >M
    0.06
    @Configuration
    0.06
    _BY
    0.06
     vale
    0.06
    /P
    0.06
    Act Density 0.014%

    No Known Activations