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

    Neuronpedia

    INDEX
    Explanations

    financial ruin, relating to, late

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รู้
    1.20
     gdy
    1.18
    nji
    1.14
    '{
    1.13
    نیم
    1.12
    n
    1.11
    inations
    1.10
    termilk
    1.09
    ک
    1.08
     ejac
    1.06
    POSITIVE LOGITS
    letos
    1.04
    Carlton
    1.02
    ]))
    1.01
    ২০
    1.01
    at
    1.00
    мі
    1.00
    seed
    1.00
    ]),
    0.99
     seeded
    0.96
     unab
    0.95
    Act Density 0.000%

    No Known Activations