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

    Neuronpedia

    INDEX
    Explanations

    image generation prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     junction
    -0.08
    isasi
    -0.07
     importantly
    -0.07
     apparently
    -0.07
     uniquely
    -0.07
     prisoner
    -0.07
     morality
    -0.07
    bhar
    -0.07
    'all
    -0.07
     desemb
    -0.07
    POSITIVE LOGITS
     folos
    0.08
     Highlight
    0.08
    0.08
     wykorzyst
    0.08
     elder
    0.07
     RTX
    0.07
     Motorsport
    0.07
     türk
    0.07
     Diverse
    0.07
     çeşit
    0.07
    Act Density 0.002%

    No Known Activations