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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Url
    -0.07
    谓
    -0.06
    .wh
    -0.06
     Fred
    -0.06
     Metodo
    -0.06
     Cole
    -0.06
    premium
    -0.06
     rude
    -0.06
    member
    -0.06
    _font
    -0.06
    POSITIVE LOGITS
    (messages
    0.07
     podrob
    0.06
     expanded
    0.06
     scaffold
    0.06
    پی
    0.06
    ushima
    0.06
     withdrew
    0.06
    Decode
    0.06
     canine
    0.06
    ifications
    0.06
    Act Density 0.002%

    No Known Activations