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

    Neuronpedia

    INDEX
    Explanations

    bleepingcomputer.com healthline.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ড
    0.74
    foreach
    0.70
    Trunc
    0.64
    ITECTURE
    0.61
    aller
    0.60
    ה
    0.60
     magnificence
    0.60
     centrales
    0.59
    Inactive
    0.59
    থ
    0.59
    POSITIVE LOGITS
    ‬‬
    0.76
    0.74
    椀
    0.68
     를
    0.68
    וי
    0.67
     lanceol
    0.66
    0.65
    0.64
    ☺
    0.64
    0.63
    Act Density 0.003%

    No Known Activations