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

    Neuronpedia

    INDEX
    Explanations

    Scientific papers

    np_max-act · gemini-2.0-flash

    phrases related to cleaving and its effects in a biological context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the very first content word (often a section‐heading or opening keyword) at the start of a new text block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     resurrect
    -0.07
     arsch
    -0.06
     तहत
    -0.06
    ala
    -0.06
     deserted
    -0.06
    erequisites
    -0.06
    ляются
    -0.06
     Erica
    -0.06
     Rai
    -0.06
     Вот
    -0.06
    POSITIVE LOGITS
     Admir
    0.07
    (length
    0.07
    oz
    0.07
    Ư
    0.06
    0.06
     forcing
    0.06
     '${
    0.06
    =Math
    0.06
     �
    0.06
    FLOW
    0.06
    Act Density 0.169%

    No Known Activations