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

    Neuronpedia

    INDEX
    Explanations

    Filipino fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    1.10
    T
    1.05
    at
    1.01
    "
    0.97
     it
    0.96
    $
    0.95
    .
    0.93
    '
    0.91
     v
    0.91
    it
    0.90
    POSITIVE LOGITS
     ayatan
    0.87
     använda
    0.85
    selfobj
    0.85
     évaluation
    0.85
     ДО
    0.84
     Ο
    0.84
    ≙
    0.82
     да
    0.81
     φα
    0.81
     одном
    0.79
    Act Density 0.002%

    No Known Activations