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

    Neuronpedia

    INDEX
    Explanations

    _ASSIGN

    np_max-act · gemini-2.0-flash

    The neuron activates on license boilerplate wording, especially phrases like “governed by a BSD-style license.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    jected
    -0.07
    одо
    -0.06
     ê
    -0.06
    че
    -0.06
     flee
    -0.06
    astic
    -0.06
    beh
    -0.06
    .Roll
    -0.06
    oop
    -0.06
    dbh
    -0.06
    POSITIVE LOGITS
    NEG
    0.07
     "${
    0.07
     Vimeo
    0.06
     Φ
    0.06
    MainFrame
    0.06
    cats
    0.06
    mousemove
    0.06
    Russia
    0.06
     Θε
    0.06
    CHAPTER
    0.06
    Act Density 0.013%

    No Known Activations