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

    Neuronpedia

    INDEX
    Explanations

    dates and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     being
    0.42
     antid
    0.42
     coinc
    0.42
     Jihad
    0.41
     Gillian
    0.39
     Gideon
    0.39
     whose
    0.38
     Coco
    0.38
     Bulls
    0.38
     rate
    0.38
    POSITIVE LOGITS
    њи
    0.46
     исторических
    0.45
    ucho
    0.41
     обществе
    0.41
    ится
    0.38
    していた
    0.38
     истори
    0.38
    ത്രി
    0.38
     істори
    0.38
    یە
    0.38
    Act Density 0.000%

    No Known Activations