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

    Neuronpedia

    INDEX
    Explanations

    Apple Production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xA8>
    1.00
     المعادله
    0.78
     ⓒ
    0.77
    0.75
    dyž
    0.74
    Youtube
    0.73
    facebook
    0.73
    0.73
     Whilst
    0.72
    ﮑ
    0.71
    POSITIVE LOGITS
    <0x89>
    1.85
     claimed
    0.84
    juk
    0.84
     jerk
    0.79
     saja
    0.77
     per
    0.77
     jer
    0.76
    mtext
    0.76
     ian
    0.75
     germ
    0.75
    Act Density 0.002%

    No Known Activations