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

    Neuronpedia

    INDEX
    Explanations

    common connecting words

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect the English infinitival marker “to.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    holm
    -0.07
    ．
    -0.06
     noop
    -0.06
    psy
    -0.06
     bande
    -0.06
     ZEND
    -0.06
    본
    -0.06
    パン
    -0.06
     redux
    -0.06
    __('
    -0.06
    POSITIVE LOGITS
     in
    0.08
     M
    0.07
     );
    0.07
    ltra
    0.06
     addUser
    0.06
    addEventListener
    0.06
     olmadan
    0.06
     LTS
    0.06
     ώρα
    0.06
     películ
    0.06
    Act Density 0.063%

    No Known Activations