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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of advisory or warning language, especially the word “important.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     starts
    -0.07
     почина
    -0.06
    Wr
    -0.06
    ！');↵
    -0.06
    Within
    -0.06
    政策
    -0.06
    имо
    -0.06
    мы
    -0.06
    ací
    -0.06
    	utils
    -0.06
    POSITIVE LOGITS
    (bean
    0.07
     katıl
    0.07
    .Struct
    0.07
    0.07
    0.07
    _TRAN
    0.07
    _TRY
    0.06
    <i
    0.06
    ,)
    0.06
    .now
    0.06
    Act Density 0.015%

    No Known Activations