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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三农
    -0.07
    胝
    -0.07
    ↲
    -0.07
     Dodgers
    -0.07
    Ᵽ
    -0.07
    ὧ
    -0.07
    システ
    -0.07
    Honda
    -0.06
     '::
    -0.06
    𬨎
    -0.06
    POSITIVE LOGITS
    _pr
    0.07
    永
    0.07
    走了
    0.07
    Dice
    0.07
     Pac
    0.07
     fract
    0.06
    progress
    0.06
     thế
    0.06
    vie
    0.06
    郄
    0.06
    Act Density 0.051%

    No Known Activations