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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    The neuron detects comparative constructions, especially the words “more” and “than” indicating a comparison.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     katı
    -0.07
    ictionary
    -0.07
     Choir
    -0.07
    porno
    -0.06
     disreg
    -0.06
    unj
    -0.06
    ��
    -0.06
    (statearr
    -0.06
    Stars
    -0.06
     Gallagher
    -0.06
    POSITIVE LOGITS
     /=
    0.07
    فی
    0.06
    GetProperty
    0.06
    =<?=$
    0.06
    خ
    0.06
     Ri
    0.06
    ;';↵
    0.06
    .getSession
    0.06
    (Text
    0.06
     Bas
    0.06
    Act Density 0.025%

    No Known Activations