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

    Neuronpedia

    INDEX
    Explanations

    numbers, percentages, years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     votre
    0.97
     people
    0.95
     your
    0.90
    ]
    0.89
    \
    0.84
    你
    0.82
    you
    0.82
    )\
    0.81
     c
    0.80
     vous
    0.79
    POSITIVE LOGITS
    Დ
    1.08
    rā
    1.07
    maları
    1.05
    🔻
    1.03
    <unused84>
    1.02
    tım
    1.00
    zov
    0.96
    Ꭼ
    0.96
    tembre
    0.96
    ananti
    0.93
    Act Density 0.001%

    No Known Activations