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

    Neuronpedia

    INDEX
    Explanations

    .”)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     campaigning
    1.99
    𝒸
    1.91
    ergic
    1.87
    emailer
    1.85
    documentclass
    1.84
    جواب
    1.77
    ermi
    1.75
    itionally
    1.72
    ede
    1.72
    ोर
    1.72
    POSITIVE LOGITS
    u
    2.16
    不及
    2.03
    reverse
    1.98
    ตรฐาน
    1.97
    pling
    1.94
     undone
    1.91
    upe
    1.91
    uwe
    1.90
    بيوتر
    1.88
    pim
    1.85
    Act Density 0.481%

    No Known Activations