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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.83
    ,
    0.80
     +
    0.77
     It
    0.77
     a
    0.76
     A
    0.75
    ...
    0.72
    -
    0.72
     it
    0.72
     ​​
    0.72
    POSITIVE LOGITS
    那么
    1.10
    ﮈ
    1.05
     tantas
    1.01
     soooo
    1.00
    <unused24>
    0.95
    ϻ
    0.91
    ánd
    0.91
     podľa
    0.90
    那麼
    0.90
     socalled
    0.89
    Act Density 0.000%

    No Known Activations