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

    Neuronpedia

    INDEX
    Explanations

    live commerce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asserts
    0.36
    OLYBD
    0.36
     psychopath
    0.36
     correlates
    0.36
     arousal
    0.35
     resultant
    0.34
     probed
    0.34
    Chars
    0.34
     初始化
    0.34
     initializing
    0.34
    POSITIVE LOGITS
    한국
    0.46
    🇮
    0.44
    旅行
    0.43
    travel
    0.42
    Travel
    0.40
    פון
    0.40
    🇵
    0.40
     한국
    0.40
     hermoso
    0.39
    ✈
    0.39
    Act Density 0.105%

    No Known Activations