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

    Neuronpedia

    INDEX
    Explanations

    architecture and stone structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    1.30
    y
    1.28
    Eff
    1.16
    и
    1.06
    స్
    1.04
    И
    1.04
    Vue
    1.03
     reforma
    1.02
    turbo
    1.00
    kele
    0.99
    POSITIVE LOGITS
     clowns
    1.40
     predicates
    1.38
    िफिकेट
    1.38
     suitors
    1.31
     postures
    1.19
    ieważ
    1.19
    RICS
    1.18
    মনসিংহ
    1.18
    slateg
    1.15
    VARCHAR
    1.13
    Act Density 0.000%

    No Known Activations