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

    Neuronpedia

    INDEX
    Explanations

    references to models in various contexts

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

    model; parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apetito
    -0.49
     geweest
    -0.48
    出版年
    -0.47
     فريبيس
    -0.47
    <?
    -0.46
    guous
    -0.45
    LookAnd
    -0.45
     proprement
    -0.45
    IntoConstraints
    -0.44
     gross
    -0.41
    POSITIVE LOGITS
     model
    0.69
    model
    0.69
    Model
    0.59
     Model
    0.58
     models
    0.58
    models
    0.57
     modelo
    0.54
    モデル
    0.52
     modellen
    0.52
     модель
    0.51
    Act Density 0.000%

    No Known Activations