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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ķ
    -0.07
    Ձ
    -0.07
    宮
    -0.07
    用电
    -0.07
    .getOwnProperty
    -0.07
    来看看吧
    -0.07
     trava
    -0.07
    �
    -0.07
    )<<
    -0.07
    棁
    -0.07
    POSITIVE LOGITS
    init
    0.08
    代理
    0.07
     ostr
    0.07
    editing
    0.07
     pound
    0.07
    /root
    0.07
    .child
    0.07
     Holt
    0.06
     Bair
    0.06
    dao
    0.06
    Act Density 0.000%

    No Known Activations