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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kotlin
    -0.07
     Som
    -0.07
    urbation
    -0.06
    $order
    -0.06
     доп
    -0.06
     decreasing
    -0.06
     sorte
    -0.06
     possibile
    -0.06
     Střed
    -0.06
     intellect
    -0.06
    POSITIVE LOGITS
    +-
    0.06
    SSID
    0.06
     decency
    0.06
    _extract
    0.06
     AT
    0.06
     ans
    0.06
    ña
    0.06
     압
    0.06
     bunny
    0.06
    .setHeader
    0.06
    Act Density 0.021%

    No Known Activations