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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elry
    -0.09
     lovers
    -0.07
     Solo
    -0.07
     iota
    -0.07
    _scheduler
    -0.07
    nger
    -0.07
     使用
    -0.07
    위
    -0.06
    plers
    -0.06
     jewellery
    -0.06
    POSITIVE LOGITS
    复兴
    0.07
    umed
    0.07
     definite
    0.06
     יום
    0.06
     получен
    0.06
    Property
    0.06
    step
    0.06
     абсолют
    0.06
     Sam
    0.06
     испол
    0.06
    Act Density 0.058%

    No Known Activations