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

    Neuronpedia

    INDEX
    Explanations

    nice

    np_max-act · gemini-2.0-flash

    The neuron flags Spanish words (esp. in a question), i.e. it activates on Spanish-language tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Arrays
    -0.07
     cave
    -0.07
    ADDING
    -0.07
    (it
    -0.06
     helper
    -0.06
     Herr
    -0.06
     addon
    -0.06
    _clean
    -0.06
     Tutor
    -0.06
     الولايات
    -0.06
    POSITIVE LOGITS
    .datas
    0.06
     jButton
    0.06
     shampoo
    0.06
     исключ
    0.06
    ?><
    0.06
     ejac
    0.06
     '',
↵
    0.06
    。',↵
    0.06
    _PM
    0.06
    .BorderSize
    0.06
    Act Density 0.169%

    No Known Activations