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

    Neuronpedia

    INDEX
    Explanations

    directed

    np_max-act · gemini-2.0-flash

    This neuron fires on the standard “present invention is directed to/ toward” phrasing that introduces what the invention does.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Payment
    -0.07
    енка
    -0.07
    _Show
    -0.06
    _EXISTS
    -0.06
    LineEdit
    -0.06
    .ml
    -0.06
    ْس
    -0.06
     mej
    -0.06
     flashed
    -0.06
     EX
    -0.06
    POSITIVE LOGITS
    ologic
    0.07
     Birleşik
    0.07
     getNext
    0.07
    agine
    0.07
    ovala
    0.07
    eguard
    0.06
     cins
    0.06
    аліст
    0.06
     �
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations