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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    details related to educational institutions and their activities.

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

    The neuron spikes on the very first word of a new paragraph or section (i.e. the token immediately following a blank‐line break).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ными
    -0.07
     چند
    -0.07
    ования
    -0.06
     γ
    -0.06
    ions
    -0.06
     goodness
    -0.06
     "*",
    -0.06
    ACY
    -0.06
    енного
    -0.06
     retarded
    -0.06
    POSITIVE LOGITS
    .↵
    0.07
    .’↵↵
    0.07
    .Disclaimer
    0.07
    ).↵
    0.07
    arest
    0.07
    %.↵
    0.07
    ैं।↵
    0.06
    ै.↵
    0.06
     ///↵
    0.06
    ें।↵
    0.06
    Act Density 0.379%

    No Known Activations