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

    Neuronpedia

    INDEX
    Explanations

    caught off guard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +="
    -0.06
    Perfect
    -0.06
    (products
    -0.06
     venues
    -0.06
    女人
    -0.06
    izados
    -0.06
     kittens
    -0.06
     vib
    -0.06
    _code
    -0.06
     reaches
    -0.06
    POSITIVE LOGITS
    expo
    0.07
    Rom
    0.07
     Gene
    0.06
    ":"/
    0.06
     Αρχ
    0.06
    論
    0.06
    .two
    0.06
    论
    0.06
    org
    0.06
     Rom
    0.06
    Act Density 0.012%

    No Known Activations