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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the word “types,” i.e. it detects occurrences of the token “types” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    amax
    -0.07
    ocre
    -0.06
     blanket
    -0.06
     Latin
    -0.06
     Cherry
    -0.06
     blankets
    -0.06
     Palmer
    -0.06
     vapor
    -0.06
    ipe
    -0.06
    Dependencies
    -0.06
    POSITIVE LOGITS
     б
    0.06
     cliente
    0.06
    自分の
    0.06
    ทำงาน
    0.06
     çocuğ
    0.06
    のお
    0.06
     국제
    0.06
    ことを
    0.06
    Frame
    0.06
    .fft
    0.06
    Act Density 0.043%

    No Known Activations