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

    Neuronpedia

    INDEX
    Explanations

    content values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.99
    s
    1.75
     Excellency
    1.47
    userInput
    1.46
    даги
    1.41
    ierung
    1.40
    portable
    1.37
    on
    1.37
    TreeNode
    1.36
    uah
    1.35
    POSITIVE LOGITS
     cheers
    1.93
     Possibly
    1.92
     SafeArea
    1.92
     conjure
    1.91
    রূপে
    1.91
     apie
    1.90
     wavefront
    1.88
     aloud
    1.87
     бан
    1.87
     attenuate
    1.84
    Act Density 0.014%

    No Known Activations