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

    Neuronpedia

    INDEX
    Explanations

    ethics, morality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PARA
    -0.07
     bufsize
    -0.07
    ))/(
    -0.06
     BUS
    -0.06
     پنج
    -0.06
    isty
    -0.06
    <message
    -0.06
    otu
    -0.06
     (=
    -0.06
    された
    -0.06
    POSITIVE LOGITS
    ُم
    0.07
     mortgages
    0.06
    .article
    0.06
    /new
    0.06
    usher
    0.06
    initWith
    0.06
     Addiction
    0.06
    Matching
    0.06
     brid
    0.05
     Shar
    0.05
    Act Density 0.005%

    No Known Activations