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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    The neuron activates on technical scientific terms—especially names of materials, instruments, methods, or experimental factors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /access
    -0.06
    (machine
    -0.06
     Rocky
    -0.06
     gunshot
    -0.06
    uspend
    -0.06
    �
    -0.06
    @Slf
    -0.06
     Latino
    -0.06
    _tag
    -0.06
     Legendary
    -0.06
    POSITIVE LOGITS
    ΙΑΚ
    0.07
    .PLL
    0.07
     Supern
    0.07
     пере
    0.07
     [_
    0.06
    也有
    0.06
     прох
    0.06
    imbus
    0.06
     виконання
    0.06
    stub
    0.06
    Act Density 0.047%

    No Known Activations