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

    Neuronpedia

    INDEX
    Explanations

    guessing game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scarcity
    0.38
    Brief
    0.38
    かし
    0.37
    曜
    0.37
    νά
    0.37
    鳴
    0.36
    Success
    0.36
    டா
    0.34
    hores
    0.34
    금융
    0.34
    POSITIVE LOGITS
     guess
    1.68
     Guess
    1.59
     guessing
    1.56
     guesses
    1.55
    Guess
    1.47
    猜
    1.47
    猜测
    1.45
    guess
    1.44
     guessed
    1.40
    guesses
    1.38
    Act Density 0.012%

    No Known Activations