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

    Neuronpedia

    INDEX
    Explanations

    algorithm analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Garry
    0.43
    ButtonPressed
    0.41
    orget
    0.41
    ieson
    0.40
    andfeel
    0.40
    ˂
    0.39
     परत
    0.38
     teens
    0.38
     <<"
    0.38
     Teens
    0.37
    POSITIVE LOGITS
    arXiv
    0.54
    $\
    0.50
     $[
    0.49
     arXiv
    0.47
    Note
    0.46
    Recall
    0.46
     Finite
    0.43
    Theorem
    0.43
    Result
    0.43
    Finite
    0.43
    Act Density 0.003%

    No Known Activations