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

    Neuronpedia

    INDEX
    Explanations

    Green Line stations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়াছে
    1.25
     Schol
    1.23
     обосно
    1.15
    ilibre
    1.12
    ectable
    1.10
     лица
    1.09
     withstand
    1.08
     Logos
    1.08
    INVISIBLE
    1.07
    書店
    1.07
    POSITIVE LOGITS
    ిల్లా
    0.96
    ירים
    0.88
    Been
    0.87
    ایش
    0.86
     baik
    0.85
    반
    0.85
     terjadinya
    0.84
    넉
    0.84
    .$,
    0.83
    ${
    0.82
    Act Density 0.000%

    No Known Activations