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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash

    The neuron flags words that denote observed changes or modulations in experimental measurements or outcomes (e.g. “response,” “changed,” “modulates,” “stress,” “migration”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     aumento
    -0.07
     fichier
    -0.07
    /gif
    -0.07
    규
    -0.06
    _proto
    -0.06
    &R
    -0.06
     花
    -0.06
     Cliente
    -0.06
    <strong
    -0.06
     icmp
    -0.06
    POSITIVE LOGITS
     disturbances
    0.07
     ceased
    0.07
     wag
    0.06
    นวย
    0.06
    にと
    0.06
    Certificates
    0.06
    нию
    0.06
     changed
    0.06
    -shift
    0.06
     Hello
    0.06
    Act Density 0.286%

    No Known Activations