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

    Neuronpedia

    INDEX
    Explanations

    intensity or degree

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )"><
    0.57
    นี้
    0.57
     지금
    0.56
     الطيب
    0.55
     gems
    0.55
    [][
    0.54
     לצ
    0.54
     успо
    0.54
     này
    0.53
    㴌
    0.53
    POSITIVE LOGITS
    募集
    0.69
     cirugía
    0.64
     کردار
    0.62
    応募
    0.59
     සෑම
    0.59
     cursor
    0.59
     affect
    0.58
     percussion
    0.58
     présentation
    0.57
    ญี่ป
    0.57
    Act Density 0.000%

    No Known Activations