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

    Neuronpedia

    INDEX
    Explanations

    mathematics and numbers

    np_max-act · gemini-2.0-flash

    This neuron selectively responds to numeral characters appearing inside numeric measurements (i.e. individual digits in multi-digit numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     různ
    -0.07
     srdce
    -0.06
     pán
    -0.06
     myšlen
    -0.06
    ,h
    -0.06
    алися
    -0.06
    ível
    -0.06
     Європ
    -0.06
     necessário
    -0.06
     listopadu
    -0.06
    POSITIVE LOGITS
    2
    0.09
    v
    0.08
    0
    0.08
    `()
    0.08
    Q
    0.07
    3
    0.07
    entity
    0.07
    8
    0.07
     Problems
    0.07
    bestos
    0.07
    Act Density 0.032%

    No Known Activations