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

    Neuronpedia

    INDEX
    Explanations

    Formatted data/code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “soil type,” i.e. when the phrase “soil type” appears.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .usage
    -0.06
    .feed
    -0.06
    VIRTUAL
    -0.06
     dee
    -0.06
    counts
    -0.06
     kız
    -0.06
    _of
    -0.06
    исс
    -0.06
    目录
    -0.06
    请输入
    -0.06
    POSITIVE LOGITS
    inet
    0.07
    070
    0.07
    ící
    0.06
     Đại
    0.06
    080
    0.06
     ±
    0.06
     Grund
    0.06
    /sub
    0.06
     belonged
    0.06
    :${
    0.06
    Act Density 0.002%

    No Known Activations