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

    Neuronpedia

    INDEX
    Explanations

    statistical significance tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Johansson
    0.66
    காற்று
    0.63
     Durchmesser
    0.61
    স
    0.59
    chanical
    0.59
     Padukone
    0.59
    anel
    0.57
     Corolle
    0.57
    ತ
    0.57
     আয়নের
    0.56
    POSITIVE LOGITS
    ،
    0.64
     <
    0.64
    í
    0.61
    }
    0.59
     &
    0.57
    يف
    0.57
    )
    0.57
    ，
    0.56
    !')
    0.55
    ]
    0.55
    Act Density 0.003%

    No Known Activations