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

    Neuronpedia

    INDEX
    Explanations

    followed

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “followed” (as in “followed by”) marking procedural step transitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Los
    -0.07
     enter
    -0.07
     cli
    -0.07
     Eh
    -0.07
     pyt
    -0.07
    )index
    -0.07
     Las
    -0.06
    my
    -0.06
    .Im
    -0.06
    工程
    -0.06
    POSITIVE LOGITS
     گزارش
    0.08
     followed
    0.07
    ................................
    0.07
    طلق
    0.06
    ................
    0.06
    .RequestParam
    0.06
    .ResponseWriter
    0.06
     مادر
    0.06
    (pop
    0.06
     Otherwise
    0.06
    Act Density 0.006%

    No Known Activations