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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash

    This neuron never activates—it appears to be dead and doesn’t respond to any text feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _nbr
    -0.07
     아
    -0.07
    Animated
    -0.06
    。あ
    -0.06
    Th
    -0.06
    ^\
    -0.06
     آنچه
    -0.06
     возраста
    -0.06
    jt
    -0.06
    stantiateViewController
    -0.06
    POSITIVE LOGITS
     compelling
    0.07
     option
    0.06
     použit
    0.06
    ahlen
    0.06
     momentum
    0.06
     lace
    0.06
    ौं
    0.06
    hel
    0.06
     london
    0.06
    سون
    0.06
    Act Density 0.011%

    No Known Activations