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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     खाल
    0.76
    碼
    0.71
    wot
    0.70
     عبر
    0.69
     Mostly
    0.69
    Mostly
    0.68
    zech
    0.67
    码
    0.67
    mostly
    0.66
    レザー
    0.66
    POSITIVE LOGITS
     ont
    1.10
     son
    1.07
    ont
    1.00
    son
    1.00
     Upon
    1.00
     upon
    0.98
    Upon
    0.97
    Son
    0.92
     Son
    0.92
    SON
    0.91
    Act Density 0.349%

    No Known Activations