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

    Neuronpedia

    INDEX
    Explanations

    /or

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find instances of the phrase “and/or” in license or documentation boilerplate.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SubMenu
    -0.07
     "<<
    -0.07
     podnik
    -0.06
    judul
    -0.06
     otras
    -0.06
     jiné
    -0.06
    蜜
    -0.06
     นาง
    -0.06
     método
    -0.06
     otros
    -0.06
    POSITIVE LOGITS
     ^{°}
    0.06
    ourney
    0.06
     pakistan
    0.06
    ırı
    0.06
     Lithuania
    0.06
     vraiment
    0.06
     kı
    0.06
    ucked
    0.06
    /
    0.06
     disproportion
    0.06
    Act Density 0.001%

    No Known Activations