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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    losure
    -0.07
    ерина
    -0.06
    Assembly
    -0.06
     borrowed
    -0.06
    stage
    -0.06
     correction
    -0.06
    _KERNEL
    -0.06
    烈
    -0.06
     visualize
    -0.06
    otope
    -0.06
    POSITIVE LOGITS
    ){
↵
↵
    0.07
     outlet
    0.06
    ject
    0.06
    .startsWith
    0.06
    ?>/
    0.06
     giàu
    0.06
     了
    0.06
    .poster
    0.06
     CRC
    0.06
     centerY
    0.06
    Act Density 0.246%

    No Known Activations