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

    Neuronpedia

    INDEX
    Explanations

    laser focused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rounds
    0.42
     prefs
    0.39
     croup
    0.38
     torrent
    0.38
     Tours
    0.37
     crowds
    0.37
     scrolls
    0.37
     ચી
    0.37
     робо
    0.37
     Tp
    0.36
    POSITIVE LOGITS
    abat
    0.43
    und
    0.42
    शिवम
    0.42
    rett
    0.39
    -}$
    0.38
    embre
    0.38
    battery
    0.38
     blaming
    0.37
    fuel
    0.36
    दयाल
    0.36
    Act Density 0.001%

    No Known Activations