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

    Neuronpedia

    INDEX
    Explanations

    buttons

    np_max-act · gemini-2.0-flash

    This neuron activates on Danish (or similarly inflected Scandinavian) words, detecting non-English tokens such as “tænd,” “sluk,” and other Danish-language morphemes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Shift
    -0.07
     Charts
    -0.06
    ailable
    -0.06
     �
    -0.06
     coffin
    -0.06
    کات
    -0.06
     передбач
    -0.06
     Croat
    -0.06
     SHIFT
    -0.06
     Glenn
    -0.06
    POSITIVE LOGITS
    pz
    0.06
    _abstract
    0.06
    ingroup
    0.06
     vx
    0.06
    ibur
    0.06
     arma
    0.06
     tạp
    0.06
    $$$$
    0.06
     ActionTypes
    0.06
    sonian
    0.06
    Act Density 0.010%

    No Known Activations