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

    Neuronpedia

    INDEX
    Explanations

    plural nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    0.41
     yake
    0.37
     उसे
    0.35
    راب
    0.35
    ється
    0.33
     an
    0.33
     అధ్యక్షుడు
    0.33
     którego
    0.33
     First
    0.32
    一款
    0.32
    POSITIVE LOGITS
     которые
    0.56
     kojima
    0.55
     цих
    0.55
    ponsored
    0.52
    pecific
    0.52
     जिनमें
    0.52
     जिनकी
    0.48
     basadas
    0.48
     amelyek
    0.48
     которыми
    0.48
    Act Density 0.102%

    No Known Activations