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

    Neuronpedia

    INDEX
    Explanations

    Quotes and snippets

    np_max-act · gemini-2.0-flash

    This neuron responds to impersonal “it is” constructions and associated modal/hedging words (it is, could, might, would) that signal speculation or uncertainty.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vascular
    -0.07
    .Update
    -0.07
    _return
    -0.07
    .mobile
    -0.06
     basics
    -0.06
     vascular
    -0.06
     contin
    -0.06
     retorno
    -0.06
    _ans
    -0.06
    .collectionView
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵
    0.07
     Sor
    0.07
    ฟร
    0.06
    amsung
    0.06
     fostering
    0.06
     обязатель
    0.06
     onFailure
    0.06
    .realpath
    0.06
    jf
    0.06
    =',
    0.06
    Act Density 0.057%

    No Known Activations