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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative teamwork or shared experiences

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

    "We" followed by capitalized letters

    np_acts-logits-general · gemini-2.0-flash

    WEKA We a input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مصادر
    -0.61
     glatt
    -0.60
    icksburg
    -0.58
     nakalista
    -0.56
    nieren
    -0.55
    aarrggbb
    -0.55
    таратура
    -0.54
     Lohan
    -0.54
    roek
    -0.54
    Tikang
    -0.53
    POSITIVE LOGITS
     Wikimedijinoj
    0.64
     Wea
    0.64
     defaultstate
    0.56
    Wea
    0.54
    ]';
    0.51
    '.$
    0.51
    =")
    0.50
     ")");
    0.49
     météo
    0.49
    vedi
    0.49
    Act Density 0.108%

    No Known Activations