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

    Neuronpedia

    INDEX
    Explanations

    say "theorem"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feedback
    -0.09
    زيل
    -0.08
    Feedback
    -0.08
    ومی
    -0.08
    .reload
    -0.08
    몇
    -0.08
    ებზე
    -0.08
    -confirm
    -0.08
     henni
    -0.08
     पुष
    -0.07
    POSITIVE LOGITS
     mixture
    0.10
     enumer
    0.10
    enumer
    0.09
     iterable
    0.09
     Iterate
    0.09
     decom
    0.09
     mixing
    0.09
     iter
    0.08
     enumerable
    0.08
     formula
    0.08
    Act Density 0.014%

    No Known Activations