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

    Neuronpedia

    INDEX
    Explanations

    key events and details in news announcements and reports

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

    previously granted actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
    лтемелер
    -0.62
    таратура
    -0.59
     OFDb
    -0.59
     Numerade
    -0.51
    UnsafeEnabled
    -0.48
     ModelRenderer
    -0.48
    Viited
    -0.47
    IntoConstraints
    -0.47
    CreateMap
    -0.46
    POSITIVE LOGITS
     previously
    0.53
     earlier
    0.52
    +#+#
    0.49
    previously
    0.47
     announced
    0.46
     wcześ
    0.45
    earlier
    0.45
    findpost
    0.45
     wcześniej
    0.43
    Previously
    0.40
    Act Density 0.087%

    No Known Activations