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

    Neuronpedia

    INDEX
    Explanations

    cooling, frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    certified
    0.80
     bravo
    0.79
     Lorraine
    0.78
     Obed
    0.76
    リート
    0.76
     Athletic
    0.76
     aerob
    0.75
     baton
    0.74
    lymp
    0.74
    ፊት
    0.74
    POSITIVE LOGITS
    ```
    0.74
     [/
    0.74
    ('/')
    0.72
     उत्सुक
    0.72
    ]-->
    0.71
    >]</
    0.71
     چون
    0.69
     spits
    0.69
     removed
    0.68
     പുറ
    0.68
    Act Density 0.000%

    No Known Activations