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

    Neuronpedia

    INDEX
    Explanations

    consequences and following actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OUTH
    0.65
    _);
    0.63
     Bibliography
    0.63
     জ্যো
    0.60
     クリーム
    0.60
    Easing
    0.60
     IUnary
    0.59
     ciência
    0.59
    <0x8D>
    0.58
    Ell
    0.58
    POSITIVE LOGITS
     hotspots
    0.61
    夲
    0.61
    ன்களை
    0.60
    トイレ
    0.59
    멱
    0.59
     processions
    0.57
    示例
    0.55
    浴室
    0.55
    祝い
    0.55
    景区
    0.54
    Act Density 0.000%

    No Known Activations