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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron responds to the “to” in instructional or imperative phrases (e.g. “to install,” “to read,” “to make sure”), effectively detecting the infinitive “to” used in step-by-step directions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Loop
    -0.07
    -group
    -0.07
     Loop
    -0.07
     같다
    -0.06
     Studio
    -0.06
    Factor
    -0.06
    .mid
    -0.06
     chore
    -0.06
     sandbox
    -0.06
     Echo
    -0.06
    POSITIVE LOGITS
    SH
    0.07
    IRS
    0.07
    ==$
    0.07
    ino
    0.07
     киш
    0.07
    eye
    0.06
    incy
    0.06
    icators
    0.06
     trh
    0.06
    !");↵
    0.06
    Act Density 0.040%

    No Known Activations