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

    Neuronpedia

    INDEX
    Explanations

    boom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    骑
    -0.08
    Piece
    -0.08
    ike
    -0.08
    两端
    -0.08
    -0.07
     Barton
    -0.07
     cross
    -0.07
     horse
    -0.07
    �
    -0.07
     ><
    -0.07
    POSITIVE LOGITS
     phá
    0.08
    -loop
    0.07
    不断完善
    0.07
    𝗽
    0.07
    _stamp
    0.07
    ynom
    0.07
     fungus
    0.07
    Ụ
    0.07
    研制
    0.06
    _experiment
    0.06
    Act Density 0.008%

    No Known Activations