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

    Neuronpedia

    INDEX
    Explanations

    encoded characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.83
    -
    0.73
     (
    0.68
     might
    0.67
     the
    0.66
     not
    0.65
     re
    0.65
     a
    0.64
     se
    0.63
     mist
    0.61
    POSITIVE LOGITS
    Hydrochloride
    0.93
    âche
    0.88
    ంబేద్కర్
    0.87
    humidité
    0.87
    乆
    0.86
    Imidazole
    0.85
    texto
    0.85
    婼
    0.85
    circledR
    0.85
    uuml
    0.83
    Act Density 0.020%

    No Known Activations