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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    书中
    -0.08
    พฤศจ
    -0.07
     SendMessage
    -0.07
    Encoding
    -0.07
    �
    -0.07
    融合
    -0.07
    post
    -0.07
    内心
    -0.07
    江东
    -0.06
    商机
    -0.06
    POSITIVE LOGITS
     aims
    0.08
    APPED
    0.07
    .wall
    0.06
    離開
    0.06
    peł
    0.06
     khá
    0.06
    ").↵↵
    0.06
    יסוד
    0.06
    paredStatement
    0.06
     glitches
    0.06
    Act Density 0.002%

    No Known Activations