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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ray
    -0.07
    Remaining
    -0.07
     Stopwatch
    -0.06
    Ten
    -0.06
    Ray
    -0.06
    ák
    -0.06
     Time
    -0.06
     Placeholder
    -0.06
    .unshift
    -0.06
     Histogram
    -0.06
    POSITIVE LOGITS
     dicho
    0.07
    .Load
    0.07
    _meta
    0.07
    (XML
    0.06
     [/
    0.06
     ativ
    0.06
     직접
    0.06
    елення
    0.06
    arently
    0.06
    ὐ
    0.06
    Act Density 0.007%

    No Known Activations