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

    Neuronpedia

    INDEX
    Explanations

    mail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    賽
    -0.07
    ip
    -0.07
     friend
    -0.07
    face
    -0.07
    加上
    -0.07
    之下
    -0.07
    WISE
    -0.07
    Pitch
    -0.07
    feld
    -0.06
    אמי
    -0.06
    POSITIVE LOGITS
    📶
    0.07
     medications
    0.07
    耳
    0.07
    みたいです
    0.07
    竘
    0.07
     반드시
    0.07
    一根
    0.07
    უ
    0.07
    Ὕ
    0.07
    栻
    0.06
    Act Density 0.001%

    No Known Activations