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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jean
    -0.07
    휑
    -0.07
    Jean
    -0.07
     tent
    -0.07
    _irq
    -0.06
     kon
    -0.06
     Gors
    -0.06
    椴
    -0.06
    億元
    -0.06
    澎
    -0.06
    POSITIVE LOGITS
    XC
    0.09
     BASIC
    0.07
    oped
    0.07
    vre
    0.07
    вели
    0.07
    👽
    0.07
    为主
    0.07
    (vs
    0.06
    .Sub
    0.06
    사이
    0.06
    Act Density 0.066%

    No Known Activations