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

    Neuronpedia

    INDEX
    Explanations

    technical computing and engineering

    np_max-act · gemini-2.0-flash

    This neuron detects hyphenated “X-to-Y” constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     OA
    -0.07
     Special
    -0.06
     Ox
    -0.06
    short
    -0.06
    Special
    -0.06
    togroup
    -0.06
    uuml
    -0.06
     membranes
    -0.06
     Players
    -0.06
     Carey
    -0.06
    POSITIVE LOGITS
    ViewModel
    0.06
     जन
    0.06
    ?></
    0.06
     ●
    0.06
    =__
    0.06
    ).[
    0.06
     Thumbnail
    0.06
    ";
    0.06
     ethos
    0.06
    +","+
    0.06
    Act Density 0.011%

    No Known Activations