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

    Neuronpedia

    INDEX
    Explanations

    Mi followed by ou or e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alam
    -0.11
    tr
    -0.10
    en
    -0.10
    ammo
    -0.10
    ossa
    -0.10
    ova
    -0.10
    ais
    -0.10
    eday
    -0.09
    alia
    -0.09
    odka
    -0.09
    POSITIVE LOGITS
    SSION
    0.21
    embros
    0.18
    ÄĻd
    0.16
    ocene
    0.14
    embro
    0.14
    rowave
    0.12
    (mi
    0.12
    ãĤĵãģª
    0.12
    itary
    0.12
    á»
    0.12
    Act Density 0.049%

    No Known Activations