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

    Neuronpedia

    INDEX
    Explanations

    Old-fashioned pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ư�
    -0.07
     zlat
    -0.06
     recurs
    -0.06
     persec
    -0.06
    รค
    -0.06
    -death
    -0.06
     gamer
    -0.06
    	cc
    -0.06
    rances
    -0.06
    Developer
    -0.06
    POSITIVE LOGITS
     انت
    0.07
     astrology
    0.07
     υπάρχουν
    0.07
     BMW
    0.07
     平
    0.06
    魚
    0.06
    434
    0.06
     Philly
    0.06
     hài
    0.06
    aturas
    0.06
    Act Density 0.014%

    No Known Activations