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

    Neuronpedia

    INDEX
    Explanations

    and followed by a consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    服务
    0.69
    🏽
    0.64
    ️
    0.61
    يمكن
    0.60
     takže
    0.60
     môžu
    0.57
     Использу
    0.57
     použív
    0.57
    ︎
    0.56
    the
    0.55
    POSITIVE LOGITS
     arrog
    0.66
     zwar
    0.66
    rogens
    0.65
     begged
    0.65
     frankly
    0.62
     angry
    0.62
     তারপরে
    0.59
     rebirth
    0.59
     whopping
    0.58
     rightly
    0.58
    Act Density 1.499%

    No Known Activations