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

    Neuronpedia

    INDEX
    Explanations

    matrices dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    衰
    -0.08
    ᖱ
    -0.07
    补充
    -0.07
     الإم
    -0.07
     mud
    -0.07
     스
    -0.07
     lungs
    -0.07
     dung
    -0.07
     reduction
    -0.07
    最低
    -0.06
    POSITIVE LOGITS
    expérience
    0.07
    (notification
    0.07
    ך
    0.07
    .insert
    0.07
    fälle
    0.07
    まり
    0.07
     plant
    0.06
    מנה
    0.06
    樘
    0.06
     Kuala
    0.06
    Act Density 0.013%

    No Known Activations