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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and attributes within organized sections of text

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

    lists words describing states or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dalších
    -0.65
     otros
    -0.64
     otras
    -0.63
     innych
    -0.62
     autres
    -0.59
    enumi
    -0.58
     lainnya
    -0.58
     başka
    -0.57
     betweenstory
    -0.56
     ďal
    -0.56
    POSITIVE LOGITS
     whereas
    0.68
    новништво
    0.65
     firstly
    0.64
     primarily
    0.60
    while
    0.60
     while
    0.60
     WHILE
    0.59
     tandis
    0.57
     predominate
    0.56
     first
    0.56
    Act Density 0.280%

    No Known Activations