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

    Neuronpedia

    INDEX
    Explanations

    Ratings and scores

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric score or rating values (especially decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ﻮ
    -0.07
     Tobacco
    -0.07
     Egg
    -0.06
     ander
    -0.06
    IndexOf
    -0.06
     laundering
    -0.06
     Piano
    -0.06
     conscience
    -0.06
    _subtitle
    -0.06
    ieten
    -0.06
    POSITIVE LOGITS
     син
    0.07
     crowds
    0.06
     utiliser
    0.06
     synonyms
    0.06
     jl
    0.06
    {x
    0.06
    -mini
    0.06
     WHEN
    0.06
     calcular
    0.06
     metaphor
    0.06
    Act Density 0.016%

    No Known Activations