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

    Neuronpedia

    INDEX
    Explanations

    engineering job titles and departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.88
    ng
    0.79
     brasile
    0.78
    ता
    0.76
    maj
    0.70
     máxima
    0.68
    ল
    0.68
    ן
    0.68
    ↵↵
    0.68
     basilaires
    0.68
    POSITIVE LOGITS
    -
    1.34
    /
    1.20
    )
    1.18
    (
    1.14
    :
    1.05
    *
    1.02
    )*
    1.01
    -*
    0.96
    at
    0.95
    ating
    0.92
    Act Density 0.000%

    No Known Activations