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

    Neuronpedia

    INDEX
    Explanations

    SSL errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addClass
    -0.07
     zz
    -0.07
     Âu
    -0.07
     Upload
    -0.07
     Pul
    -0.07
    	tx
    -0.07
     projection
    -0.07
    /user
    -0.07
     Put
    -0.07
     AGRE
    -0.06
    POSITIVE LOGITS
     mg
    0.07
    룁
    0.07
     beverage
    0.07
    筻
    0.07
    短信
    0.07
    ופן
    0.07
    왬
    0.06
    鲥
    0.06
     drank
    0.06
    领跑
    0.06
    Act Density 0.001%

    No Known Activations