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

    Neuronpedia

    INDEX
    Explanations

    (input

    np_max-act · gemini-2.0-flash

    The neuron fires on CamelCase code identifiers—i.e. R/Shiny function or class names written in mixed‐case.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -mediated
    -0.06
    .ReadByte
    -0.06
     ('\
    -0.06
     vỏ
    -0.06
     spirited
    -0.06
     disreg
    -0.06
     انسانی
    -0.06
    _sheet
    -0.06
    Builder
    -0.06
    `\
    -0.05
    POSITIVE LOGITS
    だけ
    0.07
     현
    0.07
    ัพ
    0.06
    goods
    0.06
     существ
    0.06
    DataType
    0.06
    ly
    0.06
     област
    0.06
    hti
    0.06
     imageUrl
    0.06
    Act Density 0.000%

    No Known Activations