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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    The neuron activates on the Russian first‐person pronoun “я.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ANTE
    -0.07
     chasing
    -0.06
     порів
    -0.06
     коли
    -0.06
    影
    -0.06
    мот
    -0.06
    atre
    -0.06
    Ｔ
    -0.06
    泛
    -0.06
    atori
    -0.06
    POSITIVE LOGITS
     cylinders
    0.07
    ..↵
    0.07
    년
    0.07
     Democratic
    0.07
    .install
    0.07
     bal
    0.06
    archs
    0.06
    _voltage
    0.06
    idlo
    0.06
    _lifetime
    0.06
    Act Density 0.013%

    No Known Activations