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

    Neuronpedia

    INDEX
    Explanations

    storm clouds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.44
    os
    1.39
    ни
    1.30
    ut
    1.27
    ah
    1.24
    ку
    1.24
    ai
    1.21
    are
    1.20
    т
    1.19
    on
    1.08
    POSITIVE LOGITS
    ט
    1.27
     assegn
    1.26
     energía
    1.13
     aé
    1.13
     przyję
    1.12
     aérea
    1.10
     étape
    1.08
     emergencia
    1.07
     escrib
    1.06
     azienda
    1.06
    Act Density 0.040%

    No Known Activations