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

    Neuronpedia

    INDEX
    Explanations

    Gemma, introduces itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ramatic
    0.44
    ību
    0.43
    伍章
    0.41
     지난해
    0.41
    graphHead
    0.41
    вили
    0.41
    gry
    0.40
    変動
    0.40
    maxcdn
    0.39
    汋
    0.39
    POSITIVE LOGITS
    timer
    0.44
     Timer
    0.44
     atrial
    0.41
     Chai
    0.41
     timer
    0.41
     parties
    0.40
     Assists
    0.40
     Social
    0.40
    raiser
    0.39
     Channels
    0.39
    Act Density 0.002%

    No Known Activations