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

    Neuronpedia

    INDEX
    Explanations

    brackets and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miscellaneous
    -0.08
     insertion
    -0.07
    -changing
    -0.07
    852
    -0.07
    Steve
    -0.07
     Broken
    -0.07
     streak
    -0.07
     maid
    -0.07
     impressions
    -0.06
    Assembler
    -0.06
    POSITIVE LOGITS
    uisine
    0.07
    .presentation
    0.07
     investments
    0.06
     совет
    0.06
    upakan
    0.06
     انسانی
    0.06
     СРСР
    0.06
    iquer
    0.06
     mainAxisAlignment
    0.06
    ики
    0.06
    Act Density 0.017%

    No Known Activations