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

    Neuronpedia

    INDEX
    Explanations

    Technical programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROPERTY
    -0.08
    𝚜
    -0.07
    Buzz
    -0.07
    ">
↵
    -0.07
    不可以
    -0.07
    𝘞
    -0.07
    azio
    -0.07
    |.↵
    -0.07
     tenga
    -0.07
     Saunders
    -0.06
    POSITIVE LOGITS
    ệt
    0.07
     gute
    0.06
     gamble
    0.06
    音响
    0.06
    _gender
    0.06
    cery
    0.06
     definitely
    0.06
     comedy
    0.06
     graphic
    0.06
     lapse
    0.06
    Act Density 0.104%

    No Known Activations