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

    Neuronpedia

    INDEX
    Explanations

    words related to programming concepts and logical constructs

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

    ending in language-specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    ressemble au netbook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordinaires
    -0.61
     sécur
    -0.60
     connues
    -0.60
     françaises
    -0.59
     sanitaires
    -0.59
     indipendente
    -0.59
     suivantes
    -0.59
     fehér
    -0.58
     équip
    -0.58
     stabilité
    -0.57
    POSITIVE LOGITS
    Autoritní
    0.79
    tvguidetime
    0.76
    Rüyada
    0.74
     disambiguazione
    0.73
    ècie
    0.73
    ngdoc
    0.70
    ipfel
    0.69
    Bibliograf
    0.64
    PreferredItem
    0.63
    msgTypes
    0.63
    Act Density 0.071%

    No Known Activations