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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لم
    -0.08
    否
    -0.07
    息息
    -0.07
    .damage
    -0.07
    寞
    -0.07
     chatting
    -0.07
     chất
    -0.07
    景色
    -0.07
     effortless
    -0.07
    買い
    -0.07
    POSITIVE LOGITS
    PEndPoint
    0.07
     tantra
    0.07
     QDir
    0.07
     Ad
    0.07
    arters
    0.07
    إدار
    0.07
     которое
    0.07
     ()↵↵
    0.07
     portraits
    0.07
    '],$
    0.07
    Act Density 0.004%

    No Known Activations