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

    Neuronpedia

    INDEX
    Explanations

    new + locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    第九
    0.75
    第五
    0.69
    阿里巴巴
    0.62
    第七
    0.61
     श्रीवास्तव
    0.61
    logits
    0.61
     Cubic
    0.61
     zeroth
    0.61
    logit
    0.59
     discredited
    0.59
    POSITIVE LOGITS
     England
    1.41
     Jersey
    1.38
     Hampshire
    1.26
    Jersey
    1.24
    England
    1.22
     Mexico
    1.16
     Inggris
    1.14
     Inglaterra
    1.13
     York
    1.12
     Britain
    1.08
    Act Density 0.009%

    No Known Activations