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

    Neuronpedia

    INDEX
    Explanations

    Met

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the prefix “Met” at the start of words (e.g. “Metabolic,” “Metastatic,” “Metachronous”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Riley
    -0.07
     Rug
    -0.07
     �
    -0.06
    ENG
    -0.06
     Pig
    -0.06
    ;$
    -0.06
     Wig
    -0.06
    ağ
    -0.06
     Williamson
    -0.06
     Singh
    -0.06
    POSITIVE LOGITS
     met
    0.12
     Met
    0.11
    Met
    0.10
     MET
    0.09
     Post
    0.08
    /met
    0.08
     Metro
    0.08
     metros
    0.07
    posts
    0.07
    metros
    0.07
    Act Density 0.021%

    No Known Activations