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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istinguish
    -0.07
    红
    -0.07
    heck
    -0.07
     endurance
    -0.07
    讲座
    -0.06
     Initializing
    -0.06
     graphics
    -0.06
     Speaking
    -0.06
    淡
    -0.06
    addEventListener
    -0.06
    POSITIVE LOGITS
    �
    0.07
    OnClick
    0.07
    pq
    0.07
    �
    0.07
     vết
    0.07
     طريق
    0.07
    ück
    0.07
    ㎰
    0.07
     guten
    0.07
     Beck
    0.07
    Act Density 0.016%

    No Known Activations