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

    Neuronpedia

    INDEX
    Explanations

    onload events, swift code, cash crops, solar system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frente
    1.59
     habido
    1.47
    એ
    1.45
    लंका
    1.43
    ამ
    1.42
    ores
    1.42
    '.$
    1.41
    р
    1.40
    "/
    1.39
    ได้รับการ
    1.38
    POSITIVE LOGITS
    c
    1.89
    ف
    1.84
    ীয়
    1.79
    cible
    1.78
    sylvania
    1.77
    ं
    1.75
    र्गत
    1.74
    न
    1.70
     asteroids
    1.66
    Celebrating
    1.65
    Act Density 0.001%

    No Known Activations