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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rall
    -0.07
    faker
    -0.06
     mụn
    -0.06
     exercitation
    -0.06
     Manga
    -0.06
     revered
    -0.06
     خون
    -0.06
    �
    -0.06
     đấu
    -0.06
    夫
    -0.06
    POSITIVE LOGITS
    .firebase
    0.07
     then
    0.06
    (sockfd
    0.06
     chụp
    0.06
     posição
    0.06
     zdraví
    0.06
     persuasive
    0.06
     knocking
    0.06
    경제
    0.06
     अध
    0.06
    Act Density 0.026%

    No Known Activations