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

    Neuronpedia

    INDEX
    Explanations

    physics approximations

    np_max-act · gemini-2.0-flash

    The neuron responds to specialized scientific or mathematical jargon—technical terms and concepts typical of academic physics and math writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     �
    -0.07
    og
    -0.07
    option
    -0.06
     му
    -0.06
    hx
    -0.06
     cbd
    -0.06
    ‪
    -0.06
    angstrom
    -0.06
     =================================================================
    -0.06
    POSITIVE LOGITS
    .createCell
    0.06
    _rr
    0.06
    538
    0.06
     einfach
    0.06
    ώσεις
    0.06
     espresso
    0.06
    variably
    0.06
    нулся
    0.06
     ridiculously
    0.06
    $instance
    0.06
    Act Density 0.006%

    No Known Activations