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

    Neuronpedia

    INDEX
    Explanations

    sets apart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     당연
    0.39
    各种
    0.38
    /\/
    0.35
    各类
    0.34
     धना
    0.34
    NSIndexPath
    0.34
    今年も
    0.34
    ísmo
    0.33
    看来
    0.33
     ఇక
    0.33
    POSITIVE LOGITS
     отличие
    2.36
     unlike
    2.30
     Unlike
    2.22
    Unlike
    2.13
     differs
    2.09
     отличи
    2.09
    unlike
    2.09
     отлича
    2.02
     distinguishes
    1.97
     differentiates
    1.97
    Act Density 0.073%

    No Known Activations