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

    Neuronpedia

    INDEX
    Explanations

    elo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &&!
    -0.08
    祝
    -0.07
    	check
    -0.07
    tip
    -0.07
    뉍
    -0.07
    帅
    -0.07
    ểm
    -0.07
    .customer
    -0.07
    点儿
    -0.07
     Semi
    -0.07
    POSITIVE LOGITS
    世界经济
    0.08
    .foreach
    0.07
     Dysfunction
    0.07
    0.07
     Scriptures
    0.07
     både
    0.07
     roś
    0.07
     Oscars
    0.07
     arousal
    0.07
     Mockito
    0.07
    Act Density 0.002%

    No Known Activations