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

    Neuronpedia

    INDEX
    Explanations

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "With
    -0.08
    眺
    -0.07
    VEN
    -0.07
     proporcion
    -0.07
     census
    -0.07
     партнер
    -0.07
    孵
    -0.07
    屏障
    -0.06
     paddingLeft
    -0.06
     listeners
    -0.06
    POSITIVE LOGITS
    velle
    0.08
    kie
    0.08
     fwrite
    0.07
    /met
    0.07
    ったら
    0.07
    月以来
    0.07
    férence
    0.07
     outcomes
    0.07
     Says
    0.07
    )){
↵
    0.07
    Act Density 0.001%

    No Known Activations