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

    Neuronpedia

    INDEX
    Explanations

    dosage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atorio
    -0.08
    ativas
    -0.07
    luetooth
    -0.07
    -banner
    -0.07
    -circle
    -0.07
     zh
    -0.06
     rouge
    -0.06
     fís
    -0.06
    agina
    -0.06
     webhook
    -0.06
    POSITIVE LOGITS
     UNITED
    0.08
    	speed
    0.06
     Debug
    0.06
    Brian
    0.06
    ."↵↵↵↵
    0.06
    007
    0.06
    urity
    0.06
     Bau
    0.06
    πή
    0.05
     مدت
    0.05
    Act Density 0.011%

    No Known Activations