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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ön
    -0.08
    ES
    -0.07
    贵州省
    -0.07
    离开了
    -0.07
    择
    -0.07
    RuntimeObject
    -0.07
    临
    -0.07
    apses
    -0.07
    ollision
    -0.07
    Muon
    -0.07
    POSITIVE LOGITS
    キレイ
    0.07
     trời
    0.07
    Grade
    0.07
    놀
    0.07
    )+(
    0.07
    �
    0.07
     flora
    0.07
    �
    0.06
    _featured
    0.06
     נוספים
    0.06
    Act Density 0.160%

    No Known Activations