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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron fires on the infinitival “to” (and its immediate context) in step‐by‐step instructional phrases (e.g. “follow to …,” “steps you can … to …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     estrogen
    -0.08
    Cas
    -0.07
    hands
    -0.07
     APP
    -0.07
    analyze
    -0.07
    Disc
    -0.06
    "On
    -0.06
    ंधन
    -0.06
    ंडल
    -0.06
     On
    -0.06
    POSITIVE LOGITS
    )e
    0.06
     proprio
    0.06
     unge
    0.06
     %[
    0.06
    ै।↵↵
    0.06
     Ao
    0.06
    ↵				↵
    0.06
    _RELEASE
    0.06
    0.06
     podnikatel
    0.06
    Act Density 0.033%

    No Known Activations