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

    Neuronpedia

    INDEX
    Explanations

    manager or director titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Еще
    1.16
    Ⴎ
    1.12
     misalkan
    1.10
    uZ
    1.07
    était
    1.06
    Estos
    1.03
    𝙰
    1.02
    eonium
    1.02
    ভৌম
    1.02
     definito
    1.01
    POSITIVE LOGITS
    ä
    1.04
    ↵
    1.02
     "
    1.00
     (
    0.99
    ↵↵
    0.97
    en
    0.96
    se
    0.94
     $
    0.93
     It
    0.91
    ally
    0.90
    Act Density 0.001%

    No Known Activations