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

    Neuronpedia

    INDEX
    Explanations

    Standing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungeon
    -0.07
    %">↵
    -0.07
    酒
    -0.06
     mobs
    -0.06
     cont
    -0.06
    fox
    -0.06
     wirklich
    -0.06
    ことも
    -0.06
     Voyager
    -0.06
     нашей
    -0.06
    POSITIVE LOGITS
    rk
    0.07
    	Test
    0.07
    .En
    0.07
    .ins
    0.07
    δί
    0.07
    Ark
    0.07
    adaptive
    0.06
     celery
    0.06
    bsd
    0.06
     addItem
    0.06
    Act Density 0.002%

    No Known Activations