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

    Neuronpedia

    INDEX
    Explanations

    ok

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -time
    -0.07
    276
    -0.07
     Wilson
    -0.06
    rength
    -0.06
    Display
    -0.06
    Wilson
    -0.06
     Score
    -0.06
    elf
    -0.06
    Benef
    -0.06
     pause
    -0.06
    POSITIVE LOGITS
    =m
    0.07
    []);↵
    0.06
     feminism
    0.06
     occupations
    0.06
    akan
    0.06
     доз
    0.06
    .tensor
    0.06
    	BufferedReader
    0.06
    <li
    0.06
     conhe
    0.06
    Act Density 0.017%

    No Known Activations