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

    Neuronpedia

    INDEX
    Explanations

    allegedly, supposedly, arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fichier
    0.73
     ótimo
    0.73
     ann
    0.72
     hepat
    0.71
    <iframe>
    0.71
    頰
    0.70
     pasti
    0.70
    Ẽ
    0.70
    excellent
    0.69
     lovely
    0.69
    POSITIVE LOGITS
     according
    1.98
     According
    1.85
     allegedly
    1.79
    According
    1.62
     supposedly
    1.59
    according
    1.56
     якобы
    1.54
     menurut
    1.52
     apparently
    1.51
     argues
    1.50
    Act Density 0.069%

    No Known Activations