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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the word “use.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    assertSame
    -0.07
    _ary
    -0.06
    ्रमण
    -0.06
     unr
    -0.06
    average
    -0.06
    .isNull
    -0.06
    rane
    -0.06
    inary
    -0.06
    assertEquals
    -0.06
    @RequestParam
    -0.06
    POSITIVE LOGITS
     THAT
    0.07
     çocuk
    0.07
     celular
    0.07
     seria
    0.07
     kids
    0.07
     كتاب
    0.07
     Cristina
    0.06
    antor
    0.06
     that
    0.06
    ें
    0.06
    Act Density 0.017%

    No Known Activations