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

    Neuronpedia

    INDEX
    Explanations

    Personality types and astrology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’am
    -0.07
    ád
    -0.07
     novels
    -0.07
    Educ
    -0.06
    'am
    -0.06
     spar
    -0.06
    bins
    -0.06
     Mär
    -0.06
    Sport
    -0.06
     Visit
    -0.06
    POSITIVE LOGITS
     pled
    0.06
    址
    0.06
    なく
    0.06
    �
    0.06
    ho
    0.06
    arpa
    0.06
    ulfill
    0.06
    /english
    0.06
     Nec
    0.06
     leo
    0.06
    Act Density 0.002%

    No Known Activations