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
    akra
    -0.07
     Tiếng
    -0.07
    ten
    -0.06
    ceeded
    -0.06
     eaten
    -0.06
     wart
    -0.06
    _STATE
    -0.06
     rockets
    -0.06
     -------------------------------------------------------------------------
    -0.06
    ší
    -0.06
    POSITIVE LOGITS
     tide
    0.07
    \Auth
    0.07
     vẻ
    0.06
    HOW
    0.06
     ticking
    0.06
     removable
    0.06
    (component
    0.06
    衡
    0.06
     excess
    0.06
    Ư
    0.06
    Act Density 0.010%

    No Known Activations