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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三个月
    -0.08
    招投标
    -0.07
    审批
    -0.07
    دق
    -0.07
    련
    -0.07
    ependency
    -0.07
    热爱
    -0.07
    andles
    -0.07
    bru
    -0.06
    目的是
    -0.06
    POSITIVE LOGITS
    aka
    0.08
    而出
    0.07
     ingestion
    0.07
    يه
    0.07
    _pitch
    0.07
    になってしまう
    0.07
    _Id
    0.07
     awake
    0.07
    ison
    0.07
     pacman
    0.06
    Act Density 0.007%

    No Known Activations