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

    Neuronpedia

    INDEX
    Explanations

    word starts with "ch"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     true
    1.06
     chief
    1.03
     Chief
    1.00
     complementary
    0.99
    親
    0.98
    sure
    0.96
     regenerated
    0.96
    orative
    0.96
     isIn
    0.93
    ானா
    0.92
    POSITIVE LOGITS
    츰
    1.39
     graphique
    1.31
    gwin
    1.30
    esterol
    1.28
    munk
    1.22
    mataspid
    1.21
    तुरंग
    1.19
    lains
    1.18
    ំពោះ
    1.17
    ំនួន
    1.14
    Act Density 0.433%

    No Known Activations