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

    Neuronpedia

    INDEX
    Explanations

    comma followed by letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cerc
    0.32
     करीब
    0.31
     अंसारी
    0.30
     गर
    0.30
     tratti
    0.29
     asos
    0.29
     punctual
    0.29
     kommt
    0.29
     kumb
    0.29
     dizzy
    0.29
    POSITIVE LOGITS
    💻
    0.33
    produce
    0.32
    robots
    0.32
    ChatGPT
    0.31
     અથવા
    0.31
     etcétera
    0.31
    or
    0.31
    数字
    0.31
    电子邮件
    0.31
     ঘোষণ
    0.30
    Act Density 0.013%

    No Known Activations