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

    Neuronpedia

    INDEX
    Explanations

    references to standards and conventional expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    standard, usual, typical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.38
     Philosophie
    -0.37
     sukienka
    -0.36
    hängigkeit
    -0.35
     électroniques
    -0.35
     Umständen
    -0.33
     kurtka
    -0.33
    énier
    -0.31
     originaux
    -0.31
    fassungs
    -0.31
    POSITIVE LOGITS
    typical
    0.76
     typical
    0.75
     CreateTagHelper
    0.72
    ftagPool
    0.70
     standard
    0.68
     Typical
    0.66
    usual
    0.65
    典型
    0.65
    contentLoaded
    0.64
    standard
    0.64
    Act Density 0.046%

    No Known Activations