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

    Neuronpedia

    INDEX
    Explanations

    code block separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Imports
    0.73
    polyfills
    0.67
    FBSDKAccessToken
    0.67
    <unused1863>
    0.67
    Toast
    0.65
    <unused351>
    0.65
    Lähteet
    0.64
     आरबीआई
    0.63
    CreateWall
    0.62
    ശ
    0.62
    POSITIVE LOGITS
     Perhaps
    1.10
    ↵↵
    1.03
     –
    0.89
     Maybe
    0.89
     Thank
    0.87
     การ
    0.87
     Of
    0.86
     Considering
    0.84
     With
    0.83
     Sitting
    0.83
    Act Density 0.015%

    No Known Activations