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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cache
    -0.06
     Chocolate
    -0.06
     queen
    -0.06
     khí
    -0.06
     whe
    -0.06
     mum
    -0.06
    _mean
    -0.06
    	response
    -0.06
    ρ
    -0.06
    』（
    -0.06
    POSITIVE LOGITS
    ูแล
    0.07
     طول
    0.06
    addle
    0.06
     Loud
    0.06
     Ré
    0.06
    sessions
    0.06
    indre
    0.06
     вол
    0.06
    élé
    0.06
    ува
    0.06
    Act Density 0.002%

    No Known Activations