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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash

    This neuron detects section heading labels, in particular the “Introduction” heading.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    quisites
    -0.08
    hou
    -0.07
     tercih
    -0.07
     Resist
    -0.06
     故
    -0.06
     hogy
    -0.06
    snake
    -0.06
    IMPLIED
    -0.06
     fou
    -0.06
    tout
    -0.06
    POSITIVE LOGITS
    	const
    0.07
    .flush
    0.07
    (itr
    0.06
    (Route
    0.06
    _DIG
    0.06
    acyj
    0.06
     splendid
    0.06
    opa
    0.06
     (;
    0.06
     outweigh
    0.06
    Act Density 0.001%

    No Known Activations