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

    Neuronpedia

    INDEX
    Explanations

    IN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bj
    -0.07
     Bernardino
    -0.06
    ्तव
    -0.06
    اده
    -0.06
    dbe
    -0.06
    مار
    -0.06
    олос
    -0.06
     recall
    -0.06
    мент
    -0.06
     transformations
    -0.06
    POSITIVE LOGITS
    FOUND
    0.07
     Broadway
    0.07
    "There
    0.07
    _Item
    0.07
     upsetting
    0.07
    icking
    0.06
    FS
    0.06
    Qualified
    0.06
    _elapsed
    0.06
    /QĐ
    0.06
    Act Density 0.002%

    No Known Activations