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

    Neuronpedia

    INDEX
    Explanations

    action, attack, weapon, system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.42
    ！（
    0.33
     ("
    0.32
     (&
    0.30
     (_
    0.29
     (“
    0.29
     글로벌
    0.29
     ((
    0.29
     (+
    0.29
     (**
    0.29
    POSITIVE LOGITS
    goers
    0.32
    speople
    0.31
    Seen
    0.29
    siswa
    0.29
    esterday
    0.28
     கூறியதாவது
    0.28
    putted
    0.28
     oameni
    0.28
    ondan
    0.28
    ﻪ
    0.27
    Act Density 0.034%

    No Known Activations