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

    Neuronpedia

    INDEX
    Explanations

    precision

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “precision,” especially when used as a technical term or title heading (e.g. “Precision of …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    airobi
    -0.07
    JECT
    -0.07
     Chemical
    -0.07
    SORT
    -0.07
     Report
    -0.07
     Anita
    -0.07
    Annual
    -0.07
    Stat
    -0.07
     Mate
    -0.07
    ARR
    -0.06
    POSITIVE LOGITS
     precision
    0.13
     Precision
    0.08
    Precision
    0.07
    -padding
    0.07
     pcm
    0.07
    ilation
    0.06
     convenience
    0.06
     trà
    0.06
     spectator
    0.06
     utiliza
    0.06
    Act Density 0.003%

    No Known Activations