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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron selectively responds to numeric constants and arithmetic/operator symbols, i.e. tokens that are parts of mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ีต
    -0.06
    ią
    -0.06
    Current
    -0.06
    Servers
    -0.06
     Ago
    -0.06
    pyx
    -0.06
    .Types
    -0.06
    Percentage
    -0.06
    เซอร
    -0.06
     Eq
    -0.06
    POSITIVE LOGITS
    Nova
    0.06
    ^.
    0.06
     createState
    0.06
     neden
    0.06
    .addAction
    0.06
    .)
    0.06
     produk
    0.06
     Semiconductor
    0.06
     修改
    0.06
    альную
    0.06
    Act Density 0.002%

    No Known Activations