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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fälle
    -0.08
    🚔
    -0.07
    ểm
    -0.07
     proximity
    -0.07
    .Broadcast
    -0.07
    Theme
    -0.07
    ーシ
    -0.07
     מקרה
    -0.07
    .ClientSize
    -0.07
    ícia
    -0.07
    POSITIVE LOGITS
    :_
    0.08
     riv
    0.07
    Eth
    0.07
    谷歌
    0.07
    Her
    0.07
    剡
    0.07
    ][]
    0.07
    收割
    0.07
    orrect
    0.07
     الأه
    0.07
    Act Density 0.004%

    No Known Activations