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

    Neuronpedia

    INDEX
    Explanations

    "," and "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     textbooks
    -0.07
    -tests
    -0.07
    ولوژی
    -0.06
     Derm
    -0.06
     utterly
    -0.06
    ाइन
    -0.06
    _start
    -0.06
     mountains
    -0.06
     SSE
    -0.06
     Rear
    -0.06
    POSITIVE LOGITS
    ción
    0.07
    .encrypt
    0.06
    (ConfigurationManager
    0.06
    +":
    0.06
    fil
    0.06
     联
    0.06
    .population
    0.06
     Masc
    0.06
     ")
    0.06
     inev
    0.06
    Act Density 0.013%

    No Known Activations