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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '**
    -0.08
     binary
    -0.06
     ${
    -0.06
     assisted
    -0.06
     Song
    -0.06
     superstar
    -0.06
    //$
    -0.06
    	audio
    -0.06
     Wan
    -0.06
    666
    -0.06
    POSITIVE LOGITS
     espionage
    0.07
     dia
    0.07
     неиз
    0.07
    ployment
    0.06
    В
    0.06
     ніколи
    0.06
     갤로그
    0.06
     exploding
    0.06
     함께
    0.06
     Sovere
    0.06
    Act Density 0.000%

    No Known Activations