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

    Neuronpedia

    INDEX
    Explanations

    social media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baller
    0.75
    ృద్ధి
    0.69
     शीत
    0.67
     yield
    0.66
    Bers
    0.65
    าร
    0.65
    છા
    0.65
    erious
    0.64
    itoral
    0.64
     randon
    0.63
    POSITIVE LOGITS
     media
    1.86
     Media
    1.61
    media
    1.54
    Media
    1.54
     MEDIA
    1.53
    媒体
    1.48
     medya
    1.42
    MEDIA
    1.39
    メディア
    1.39
     medias
    1.39
    Act Density 0.071%

    No Known Activations