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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of prices or cost expressions (e.g., currency symbols with numbers or "each" in price contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IDE
    -0.06
    _Surface
    -0.06
    ImageData
    -0.06
     fences
    -0.06
    CONNECT
    -0.06
     printk
    -0.06
     　　　　　　
    -0.06
    letics
    -0.06
    _compress
    -0.06
     thermal
    -0.06
    POSITIVE LOGITS
    \":\"
    0.07
    .MON
    0.07
     emanc
    0.07
     dvoj
    0.07
     část
    0.06
    .keep
    0.06
     hurt
    0.06
     seab
    0.06
     prototypes
    0.06
     ${↵
    0.06
    Act Density 0.009%

    No Known Activations