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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, particularly those related to the past

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

    reference to past time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.65
     الحره
    -0.56
    parsedMessage
    -0.55
     ModelRenderer
    -0.54
     autorytatywna
    -0.54
    DIPSETTING
    -0.51
    adaptiveStyles
    -0.51
     Comprometido
    -0.50
    writeFieldEnd
    -0.49
     dětí
    -0.49
    POSITIVE LOGITS
     weekend
    0.78
     week
    0.77
     month
    0.76
     decade
    0.73
     year
    0.68
     summer
    0.61
    /*
    0.56
     few
    0.55
     winter
    0.53
     two
    0.51
    Act Density 0.020%

    No Known Activations