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

    Neuronpedia

    INDEX
    Explanations

    words starting with an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蠵
    0.40
    supportsFocus
    0.35
    SDLCheck
    0.35
     सूर्
    0.34
     Oldborough
    0.34
    棫
    0.34
    喤
    0.34
    шенный
    0.33
    rrggbb
    0.33
     Loksatta
    0.33
    POSITIVE LOGITS
     An
    3.42
    An
    3.30
    <0x8E>
    3.11
     AN
    2.97
     Ан
    2.92
     ан
    2.80
     Annette
    2.50
    アン
    2.47
     anem
    2.45
     anise
    2.44
    Act Density 0.118%

    No Known Activations