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

    Neuronpedia

    INDEX
    Explanations

    wordle related guesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     begin
    -0.77
     Precambrian
    -0.76
     twelve
    -0.73
    😋
    -0.71
    сни
    -0.71
     during
    -0.71
     magicians
    -0.71
     thirteen
    -0.70
     Poisson
    -0.69
    ياه
    -0.69
    POSITIVE LOGITS
     Wordle
    1.20
    guess
    1.16
     guess
    1.14
     guesses
    1.04
    Guess
    0.98
     guessed
    0.92
     tact
    0.87
    guesses
    0.87
     Hồng
    0.85
     Guess
    0.84
    Act Density 0.003%

    No Known Activations