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

    Neuronpedia

    INDEX
    Explanations

    . , formal, formatted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rabb
    0.39
     trium
    0.38
    लीस
    0.37
     Beverage
    0.36
     timer
    0.36
     pair
    0.35
     рынок
    0.35
    pair
    0.35
     rabbit
    0.35
     QUI
    0.35
    POSITIVE LOGITS
    IPL
    0.38
    ML
    0.37
     aplikace
    0.37
    ចាំ
    0.37
     rosa
    0.36
    {#
    0.36
     என்னை
    0.36
    plica
    0.36
    ോഷ
    0.35
    PL
    0.35
    Act Density 0.000%

    No Known Activations