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

    Neuronpedia

    INDEX
    Explanations

    numbers in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sidhu
    0.44
     Good
    0.42
     गुड
    0.41
    plet
    0.39
     muestran
    0.39
    િયલ
    0.39
     Lucien
    0.39
     Steph
    0.38
    راحی
    0.38
    ነስ
    0.37
    POSITIVE LOGITS
    Aik
    0.43
    AI
    0.42
    Inn
    0.40
     Hund
    0.39
    ITES
    0.39
    igence
    0.38
     warmth
    0.38
    shall
    0.37
    Ire
    0.37
     sheaves
    0.36
    Act Density 0.000%

    No Known Activations