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

    Neuronpedia

    INDEX
    Explanations

    type declarations or union types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Specimens
    0.40
     norm
    0.39
    𐰆
    0.38
     normed
    0.38
     (?)
    0.37
     (),
    0.37
     Norm
    0.37
    Norm
    0.36
     suppl
    0.36
    نامج
    0.35
    POSITIVE LOGITS
     |
    1.59
    |
    1.28
    |\
    1.02
     |\
    0.97
    |(
    0.95
     $|\
    0.94
     $|
    0.91
     |.
    0.89
    |.
    0.88
    ❘
    0.86
    Act Density 0.016%

    No Known Activations