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

    Neuronpedia

    INDEX
    Explanations

    i'm focusing on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.55
    zną
    1.24
    й
    1.14
    ي
    1.13
    at
    1.06
    ist
    1.05
    ა
    1.04
     bleibt
    0.99
    ige
    0.96
    أم
    0.96
    POSITIVE LOGITS
    tri
    1.13
    t
    1.05
    trip
    1.01
    risy
    1.01
    soever
    1.00
    speople
    1.00
    traf
    0.98
    structed
    0.98
     §§
    0.97
    tarif
    0.97
    Act Density 0.105%

    No Known Activations