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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numeric tokens, i.e. it detects numbers (numerals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    artist
    -0.07
     frightened
    -0.07
     ensured
    -0.07
    이스
    -0.07
     both
    -0.06
     Scal
    -0.06
    μένες
    -0.06
     organised
    -0.06
    �
    -0.06
     موج
    -0.06
    POSITIVE LOGITS
     nine
    0.07
    系列
    0.07
    ('&
    0.06
     Seks
    0.06
    .ReadLine
    0.06
    592
    0.06
    Nine
    0.06
    .Package
    0.06
    EXT
    0.06
     Viktor
    0.06
    Act Density 0.062%

    No Known Activations