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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “such” when it’s used to introduce examples (as in “such as”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    on
    -0.09
    atır
    -0.07
     Gordon
    -0.07
    ारत
    -0.07
     Erl
    -0.07
    'on
    -0.07
    ON
    -0.07
    ioni
    -0.07
    rl
    -0.07
    ot
    -0.07
    POSITIVE LOGITS
     such
    0.13
     SUCH
    0.10
    such
    0.10
    Such
    0.09
     Such
    0.08
    اک
    0.08
     Hash
    0.08
    ３
    0.08
    sch
    0.08
    usch
    0.07
    Act Density 0.097%

    No Known Activations