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

    Neuronpedia

    INDEX
    Explanations

    countdown or sequence of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    栦
    0.43
    Js
    0.41
    Scrim
    0.40
    Emojis
    0.40
    সাম্প্র
    0.40
     आतंकी
    0.39
    谣
    0.39
    Charges
    0.39
    Bomb
    0.39
    штейн
    0.39
    POSITIVE LOGITS
     -
    0.50
     --
    0.45
     T
    0.42
     –
    0.41
     Q
    0.40
    ↵
    0.39
     _
    0.38
    …
    0.38
    fl
    0.38
     R
    0.37
    Act Density 0.003%

    No Known Activations