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

    Neuronpedia

    INDEX
    Explanations

    Heretrainloopvirus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಮಕ್ಕಳ
    0.45
     CONCEPT
    0.42
    鲸
    0.41
     grandparent
    0.40
     ಮಕ್ಕ
    0.39
     círculo
    0.38
     الخلق
    0.38
    껌
    0.38
     법칙
    0.38
     बच्चों
    0.38
    POSITIVE LOGITS
    Here
    0.50
    يره
    0.47
    sure
    0.42
    ere
    0.41
    here
    0.41
    In
    0.40
     Here
    0.38
    erer
    0.38
    soph
    0.38
     toutes
    0.37
    Act Density 0.000%

    No Known Activations