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

    Neuronpedia

    INDEX
    Explanations

    HTML table rows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Top
    -0.07
     pill
    -0.07
     MESSAGE
    -0.07
    timer
    -0.07
     Heroes
    -0.07
     economies
    -0.06
    rectangle
    -0.06
    칭
    -0.06
    INES
    -0.06
    (history
    -0.06
    POSITIVE LOGITS
     vigorously
    0.07
    َي
    0.07
    ，加
    0.06
    �
    0.06
    teborg
    0.06
    ogens
    0.06
    0.06
    ้าท
    0.06
    itative
    0.06
     경기도
    0.06
    Act Density 0.007%

    No Known Activations