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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash

    stories that evoke feelings of joy and companionship through animal characters.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is triggered by floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     irm
    -0.07
    DIV
    -0.07
    LEC
    -0.06
     Госп
    -0.06
    INGLE
    -0.06
    лась
    -0.06
     oat
    -0.06
    (member
    -0.06
    ्थल
    -0.06
     CWE
    -0.06
    POSITIVE LOGITS
     brochure
    0.06
     pays
    0.06
    -bottom
    0.06
     Points
    0.06
     Intel
    0.06
    する
    0.06
    scroll
    0.06
     fitness
    0.06
    xFFF
    0.06
    eea
    0.06
    Act Density 0.001%

    No Known Activations