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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is essentially inactive and does not detect or respond to any token patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ******↵
    -0.07
     강남
    -0.06
    quivo
    -0.06
     Ин
    -0.06
     visceral
    -0.06
    ěstí
    -0.06
    _operator
    -0.06
    xFD
    -0.06
    imi
    -0.06
     Paradise
    -0.06
    POSITIVE LOGITS
     rec
    0.07
     trif
    0.07
     ख
    0.06
     iOS
    0.06
     उच
    0.06
     Νο
    0.06
    .bpm
    0.06
    生活
    0.06
     policymakers
    0.06
     conjunto
    0.06
    Act Density 0.017%

    No Known Activations