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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elliott
    -0.07
    _stmt
    -0.06
     winter
    -0.06
    ROC
    -0.06
     paycheck
    -0.06
     contest
    -0.06
    neider
    -0.06
     Davis
    -0.06
     publishing
    -0.06
     florida
    -0.06
    POSITIVE LOGITS
    Temperature
    0.07
     %%
    0.07
     ')';↵
    0.07
     встанов
    0.06
    .sk
    0.06
    htmlspecialchars
    0.06
    |[
    0.06
    (matrix
    0.06
     plunged
    0.06
    .$
    0.06
    Act Density 0.007%

    No Known Activations