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

    Neuronpedia

    INDEX
    Explanations

    break, map, prioritize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    1.53
    то
    1.40
    ম
    1.38
    র
    1.31
     사항
    1.28
    да
    1.25
    те
    1.24
    c
    1.23
    ד
    1.23
    ক
    1.20
    POSITIVE LOGITS
    1.13
     मिलकर
    1.09
    pecific
    1.00
    }></
    0.99
     ensu
    0.98
    적으로
    0.97
     serem
    0.97
    aus
    0.96
    aal
    0.96
     riguardo
    0.96
    Act Density 0.218%

    No Known Activations