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 detects numeric substrings representing floating-point numbers (decimal activations) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ov
    -0.06
     Fe
    -0.06
     Darling
    -0.06
     Mack
    -0.06
    dto
    -0.06
    isms
    -0.06
     несколь
    -0.06
    搜索
    -0.06
    bling
    -0.06
    docs
    -0.06
    POSITIVE LOGITS
    _HANDLE
    0.07
     taxi
    0.07
     queryString
    0.06
    atLng
    0.06
    ανδ
    0.06
     �
    0.06
    >::
    0.06
     Word
    0.06
     nostr
    0.06
    '),
↵
    0.06
    Act Density 0.127%

    No Known Activations