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

    Neuronpedia

    INDEX
    Explanations

    do this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devoured
    0.52
     jaguar
    0.48
    女
    0.47
     vostro
    0.44
     healed
    0.43
     steamer
    0.43
     nowy
    0.42
     jew
    0.42
     your
    0.42
     souvenirs
    0.42
    POSITIVE LOGITS
     này
    1.48
     этого
    1.39
     этом
    1.37
     هذا
    1.33
     этой
    1.31
     этих
    1.30
     هذه
    1.29
     this
    1.24
     these
    1.21
     это
    1.21
    Act Density 0.039%

    No Known Activations