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

    Neuronpedia

    INDEX
    Explanations

    domain registrars and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TA
    0.96
     NC
    0.90
    ters
    0.88
    рия
    0.87
    TE
    0.86
     DV
    0.86
    }]
    0.84
     ALL
    0.82
     hallway
    0.82
     NA
    0.80
    POSITIVE LOGITS
    м
    1.27
     rossa
    1.13
     branca
    1.11
    nél
    1.10
    این
    1.09
    Dopo
    1.09
     avevo
    1.09
    物に
    1.09
     blanca
    1.07
    发行
    1.06
    Act Density 0.001%

    No Known Activations