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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itating
    -0.07
    693
    -0.07
    iful
    -0.07
    urat
    -0.06
    268
    -0.06
    jectory
    -0.06
    氣
    -0.06
     mez
    -0.06
    聚
    -0.06
    leness
    -0.06
    POSITIVE LOGITS
     ToString
    0.07
     závis
    0.07
    stdio
    0.06
     reflection
    0.06
    post
    0.06
    '";
↵
    0.06
    $client
    0.06
    .,↵
    0.06
     type
    0.06
    	RTLU
    0.06
    Act Density 0.003%

    No Known Activations