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

    Neuronpedia

    INDEX
    Explanations

    Creation/Publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     backstory
    -0.06
     rm
    -0.06
    (OS
    -0.06
     arrogant
    -0.06
    楽し
    -0.06
    φό
    -0.06
     WHY
    -0.06
    index
    -0.06
     gems
    -0.06
     ~/
    -0.06
    POSITIVE LOGITS
    ाध
    0.08
    _password
    0.07
    сю
    0.07
     sister
    0.07
    -registration
    0.07
     Southwest
    0.06
     Vie
    0.06
    _attachment
    0.06
    -not
    0.06
     Faster
    0.06
    Act Density 0.053%

    No Known Activations