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

    Neuronpedia

    INDEX
    Explanations

    4-hmac, 4g/5g, 4.0.3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atation
    0.43
     wed
    0.40
    dala
    0.40
     materials
    0.39
     diaries
    0.38
     "
    0.37
     Gives
    0.35
     Journal
    0.35
     Materials
    0.35
    šit
    0.35
    POSITIVE LOGITS
    Extended
    0.43
     mutlaka
    0.42
     veloce
    0.42
    <0x94>
    0.40
    Dónde
    0.39
     ঢেউ
    0.39
     урок
    0.38
     reel
    0.38
    خصة
    0.38
     qualcosa
    0.37
    Act Density 0.000%

    No Known Activations