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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igor
    -0.07
     Tre
    -0.07
    anic
    -0.06
     Kal
    -0.06
    riet
    -0.06
    expanded
    -0.06
    /fixtures
    -0.06
     základě
    -0.06
    shipment
    -0.06
    _fail
    -0.06
    POSITIVE LOGITS
    ่วย
    0.07
     Cornell
    0.07
     remove
    0.07
     Inv
    0.06
    ارج
    0.06
    ，這
    0.06
     点
    0.06
    ฑ
    0.06
    ُع
    0.06
    *↵↵
    0.06
    Act Density 0.000%

    No Known Activations