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

    Neuronpedia

    INDEX
    Explanations

    embark on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒓
    0.93
    ться
    0.89
    autoplay
    0.88
    kania
    0.88
    \)
    0.86
    U
    0.84
     penalties
    0.84
     cartoons
    0.83
     Caesar
    0.83
     precipitate
    0.82
    POSITIVE LOGITS
     polled
    1.07
    ف
    1.03
    ম
    1.00
    क
    1.00
     данный
    0.98
    よかった
    0.97
    striatis
    0.97
    בוע
    0.96
    ustainable
    0.94
    ే
    0.94
    Act Density 0.001%

    No Known Activations