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

    Neuronpedia

    INDEX
    Explanations

    responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    覽
    -0.08
     member
    -0.08
    oped
    -0.08
     Allen
    -0.07
     Auschwitz
    -0.07
    mitglied
    -0.07
     members
    -0.07
     irrespons
    -0.07
     বিশ্বাস
    -0.07
     dårlig
    -0.07
    POSITIVE LOGITS
     randomized
    0.08
     станет
    0.08
     phr
    0.08
     голос
    0.07
    Preset
    0.07
     phrases
    0.07
     habitual
    0.07
    _sent
    0.07
     бот
    0.07
    机器人
    0.07
    Act Density 0.003%

    No Known Activations