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

    Neuronpedia

    INDEX
    Explanations

    anger or difficult emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ी
    0.43
    ipers
    0.40
     Mankind
    0.38
     xs
    0.37
     eh
    0.37
     Mosley
    0.37
    pb
    0.37
     ehm
    0.37
     сигна
    0.36
     composta
    0.36
    POSITIVE LOGITS
    Barrier
    0.39
    ometown
    0.37
    änd
    0.37
     напа
    0.37
    лыгы
    0.37
     tathapi
    0.36
    ätta
    0.35
    raint
    0.35
    義務
    0.35
    ruct
    0.34
    Act Density 0.013%

    No Known Activations