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

    Neuronpedia

    INDEX
    Explanations

    UI elements/scrolling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，其中
    -0.07
     �
    -0.06
    595
    -0.06
    รษฐ
    -0.06
    704
    -0.06
    商
    -0.06
     march
    -0.06
    房屋
    -0.06
    essages
    -0.06
    اما
    -0.06
    POSITIVE LOGITS
    implify
    0.07
    _event
    0.07
    _initializer
    0.07
    直播
    0.06
    _AUD
    0.06
     ammo
    0.06
    constitutional
    0.06
    lb
    0.06
     SGD
    0.06
    .instances
    0.06
    Act Density 0.349%

    No Known Activations