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

    Neuronpedia

    INDEX
    Explanations

    wherever

    np_max-act · gemini-2.0-flash

    The neuron detects location‐indicating words or adverbial connectors (e.g. “where,” “anywhere,” “wherever”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     vat
    -0.07
    toggleClass
    -0.07
     tek
    -0.07
    制造
    -0.07
    .Subscribe
    -0.06
    .setMax
    -0.06
    .SelectSingleNode
    -0.06
     onPause
    -0.06
     StreamWriter
    -0.06
    SqlParameter
    -0.06
    POSITIVE LOGITS
     wherever
    0.08
     everywhere
    0.07
     Citizenship
    0.06
    (newValue
    0.06
     anywhere
    0.06
    .ic
    0.06
     zip
    0.06
    _ack
    0.06
    _DECLS
    0.06
     located
    0.06
    Act Density 0.008%

    No Known Activations