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

    Neuronpedia

    INDEX
    Explanations

    references to publication details and notes in research articles

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

    publication history and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prohibido
    -0.37
     finanzas
    -0.37
     niega
    -0.34
     Masuk
    -0.33
     pérdidas
    -0.33
     detención
    -0.32
    Jesús
    -0.32
     Jésus
    -0.32
     últimos
    -0.32
     revisa
    -0.31
    POSITIVE LOGITS
    publication
    0.81
     publication
    0.80
     Publication
    0.76
    Publication
    0.72
     publishing
    0.70
     出版
    0.70
     publish
    0.68
     publisher
    0.67
    SequentialGroup
    0.67
    publish
    0.66
    Act Density 0.008%

    No Known Activations