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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newVal
    -0.09
     winters
    -0.07
    Tri
    -0.07
    áhnout
    -0.07
    setChecked
    -0.06
     Tri
    -0.06
    EXPECTED
    -0.06
     repeats
    -0.06
     wollen
    -0.06
     CascadeType
    -0.06
    POSITIVE LOGITS
    iram
    0.07
     سرم
    0.07
    民
    0.06
    .Display
    0.06
    สอบ
    0.06
    учас
    0.06
    ΜΑ
    0.06
     корист
    0.06
     nightlife
    0.06
     име
    0.06
    Act Density 0.016%

    No Known Activations