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

    Neuronpedia

    INDEX
    Explanations

    Act/law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cie
    -0.07
    urniture
    -0.07
    )},↵
    -0.07
    /cal
    -0.07
    Develop
    -0.07
    -FIRST
    -0.07
    cers
    -0.07
     minHeight
    -0.07
    點
    -0.07
    LE
    -0.07
    POSITIVE LOGITS
     ATS
    0.07
     управ
    0.07
    скоп
    0.07
    ✎
    0.06
     autonom
    0.06
     registr
    0.06
     informat
    0.06
    enddate
    0.06
    ❡
    0.06
     عند
    0.06
    Act Density 0.066%

    No Known Activations