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

    Neuronpedia

    INDEX
    Explanations

    Javascript "const"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    大学毕业
    -0.07
     Giám
    -0.07
    .toolStrip
    -0.07
     collusion
    -0.07
    _typeDefinition
    -0.07
     לפע
    -0.07
    _Menu
    -0.07
    鹔
    -0.07
    踺
    -0.06
    POSITIVE LOGITS
     ```↵
    0.07
    坑
    0.07
    qli
    0.07
    时期
    0.07
     Ferm
    0.07
     spl
    0.07
    GRA
    0.07
    ()];↵
    0.07
    brick
    0.07
    ALE
    0.07
    Act Density 0.012%

    No Known Activations