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

    Neuronpedia

    INDEX
    Explanations

    since

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Європ
    -0.08
     випадку
    -0.07
     /*!↵
    -0.06
     persec
    -0.06
     barrier
    -0.06
     Ish
    -0.06
     начала
    -0.06
    currentColor
    -0.06
    missive
    -0.06
     ARG
    -0.06
    POSITIVE LOGITS
    [Any
    0.07
     Interstate
    0.07
    574
    0.07
     shrimp
    0.06
    363
    0.06
    .mar
    0.06
    .ONE
    0.06
    ohen
    0.06
     تهیه
    0.06
     veggies
    0.06
    Act Density 0.001%

    No Known Activations