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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airplanes
    -0.07
    徙
    -0.07
     surfaced
    -0.07
    坜
    -0.07
    KeyListener
    -0.07
    狠
    -0.07
    冏
    -0.07
    行列
    -0.06
    认真
    -0.06
    辚
    -0.06
    POSITIVE LOGITS
    }@
    0.07
    ####
    0.07
     HOST
    0.07
    reau
    0.07
    _MONTH
    0.07
    eteria
    0.07
    -bot
    0.07
    noon
    0.07
    (PATH
    0.06
     avant
    0.06
    Act Density 0.211%

    No Known Activations