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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CHIP
    -0.07
     Protestant
    -0.07
     magnet
    -0.07
     opt
    -0.07
     timeval
    -0.07
     vit
    -0.06
     dull
    -0.06
    Ж
    -0.06
     ml
    -0.06
    HV
    -0.06
    POSITIVE LOGITS
    CustomAttributes
    0.07
    ucceed
    0.07
     흐
    0.06
     ＞
    0.06
    )})
    0.06
     ade
    0.06
     muốn
    0.06
    ({},
    0.06
    �
    0.06
     พ
    0.06
    Act Density 0.027%

    No Known Activations