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

    Neuronpedia

    INDEX
    Explanations

    disclaimer

    np_max-act · gemini-2.0-flash

    The neuron activates on license‐header/disclaimer boilerplate text—particularly the phrase “DISCLAIMER OF ALL WARRANTIES.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     留
    -0.07
    シ
    -0.06
     }}>{
    -0.06
     chờ
    -0.06
    меш
    -0.06
    ��
    -0.06
     Yaş
    -0.06
    携
    -0.06
    เว
    -0.06
    Showing
    -0.06
    POSITIVE LOGITS
     Asi
    0.08
     transparent
    0.07
     п
    0.07
     Гри
    0.06
    ,↵↵↵
    0.06
     undecided
    0.06
     permanent
    0.06
    SCORE
    0.06
    519
    0.06
    ций
    0.06
    Act Density 0.002%

    No Known Activations