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

    Neuronpedia

    INDEX
    Explanations

    curses for interactive programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.47
     그러면은
    0.47
     stoked
    0.46
    imento
    0.44
    ards
    0.44
    Techn
    0.44
     fleece
    0.43
     এসময়
    0.43
     нюан
    0.43
    astro
    0.42
    POSITIVE LOGITS
    传染
    0.47
    关于
    0.46
    decompose
    0.46
    为
    0.45
    จาก
    0.45
    蝮
    0.45
    从
    0.44
     :"
    0.44
    进行了
    0.44
     Commands
    0.44
    Act Density 0.001%

    No Known Activations