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

    Neuronpedia

    INDEX
    Explanations

    spherical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necesitar
    0.52
     composite
    0.50
     salary
    0.49
     یا
    0.47
     Rhode
    0.47
     backcountry
    0.47
     surety
    0.46
     น้ำ
    0.46
     veya
    0.46
     smoothie
    0.45
    POSITIVE LOGITS
    0
    0.54
    2
    0.53
    9
    0.50
    作者
    0.47
    口罩
    0.47
    出的
    0.44
     کارگرد
    0.44
    5
    0.44
     výraz
    0.44
     onChanged
    0.44
    Act Density 0.000%

    No Known Activations