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

    Neuronpedia

    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     briefing
    -0.08
    Pi
    -0.07
    NJ
    -0.07
    Rotor
    -0.07
    eket
    -0.07
    خاب
    -0.07
     perguntas
    -0.07
     Pi
    -0.07
     Auschwitz
    -0.07
     greetings
    -0.07
    POSITIVE LOGITS
     reckless
    0.11
     unexpected
    0.09
     неожидан
    0.09
     неож
    0.08
    σε
    0.08
    Unexpected
    0.08
    改单
    0.08
     überrasch
    0.08
     careless
    0.07
     혼
    0.07
    Act Density 0.000%

    No Known Activations