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

    Neuronpedia

    INDEX
    Explanations

    Expectation, causation, foundation, inspiration, manifestation, interpretation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tendulkar
    0.47
    紶
    0.47
    overrightarrow
    0.43
    лізу
    0.42
     Connectivity
    0.41
     तेंदुलकर
    0.41
    connectivity
    0.40
    threading
    0.40
     Ninh
    0.40
     useNavigate
    0.39
    POSITIVE LOGITS
    ation
    1.92
    ations
    1.80
    tion
    1.78
    ATION
    1.71
    ition
    1.62
     tion
    1.59
    stion
    1.53
    tions
    1.49
    ationen
    1.48
    ction
    1.48
    Act Density 0.114%

    No Known Activations