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

    Neuronpedia

    INDEX
    Explanations

    ali prefix, aliens, alibi, aliexpress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Internet
    0.41
    Gui
    0.40
     allergy
    0.39
     Universe
    0.39
    ♦
    0.38
    creet
    0.37
     grow
    0.36
     Grow
    0.36
    Peace
    0.36
    oury
    0.35
    POSITIVE LOGITS
    ases
    0.46
    ас
    0.43
     بابا
    0.43
    пат
    0.42
     बाबा
    0.42
    िलास
    0.41
    शान
    0.39
     جناح
    0.39
    ias
    0.38
     लॉन्
    0.38
    Act Density 0.006%

    No Known Activations