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

    Neuronpedia

    INDEX
    Explanations

    Scientific data

    np_max-act · gemini-2.0-flash

    The neuron never activates—it doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     کو
    -0.06
     tä
    -0.06
     مقام
    -0.06
     Markt
    -0.06
     rats
    -0.06
    ATED
    -0.06
    (activity
    -0.06
     بات
    -0.06
     děl
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     happened
    0.07
    �
    0.07
    ंग
    0.07
    |=
    0.06
     meant
    0.06
    studio
    0.06
     promptly
    0.06
    UniformLocation
    0.06
     nuôi
    0.06
    _MESSAGES
    0.06
    Act Density 0.003%

    No Known Activations