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

    Neuronpedia

    INDEX
    Explanations

    vulnerability/susceptibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    しい
    -0.07
    /Add
    -0.07
     completo
    -0.06
    рии
    -0.06
    (object
    -0.06
     авг
    -0.06
     kvinne
    -0.06
     concise
    -0.06
     Older
    -0.06
    Resizable
    -0.06
    POSITIVE LOGITS
    sob
    0.08
    扫
    0.08
    WSTR
    0.07
     Freddy
    0.07
     Dai
    0.06
     constexpr
    0.06
     cigaret
    0.06
    _terminal
    0.06
     DriverManager
    0.06
    educt
    0.06
    Act Density 0.089%

    No Known Activations