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
    kv
    -0.07
    finger
    -0.07
    ながら
    -0.07
     Clara
    -0.07
    antt
    -0.07
    签下
    -0.06
     marble
    -0.06
     Middle
    -0.06
    Training
    -0.06
    ван
    -0.06
    POSITIVE LOGITS
    @ResponseBody
    0.08
    Confirmed
    0.07
     homophobic
    0.07
    _lin
    0.07
    	ct
    0.07
     beasts
    0.07
    _UNIFORM
    0.07
    自信
    0.07
    本场比赛
    0.07
     circumcision
    0.06
    Act Density 0.002%

    No Known Activations