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

    Neuronpedia

    INDEX
    Explanations

    identify and resolve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    1.40
    in
    1.22
    ী
    1.16
    A
    1.16
    c
    1.03
    نى
    1.02
    رهای
    0.99
    precise
    0.96
    الص
    0.95
    ních
    0.95
    POSITIVE LOGITS
     cláus
    1.02
    '
    1.01
     varietà
    0.98
     বদি
    0.98
     Repubblica
    0.97
    说
    0.96
     siquiera
    0.94
    .'
    0.93
     seguramente
    0.93
    եք
    0.93
    Act Density 0.034%

    No Known Activations