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

    Neuronpedia

    INDEX
    Explanations

    acknowledgment and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aham
    0.78
     keluar
    0.77
     Now
    0.74
    ഹ്ലാ
    0.73
     Hartree
    0.72
    洊
    0.71
     Citrix
    0.70
     Thou
    0.70
     अब
    0.70
     이제
    0.69
    POSITIVE LOGITS
    ```
    1.09
    Okay
    0.95
    Subject
    0.90
    **
    0.85
    Option
    0.82
    okay
    0.81
    **(
    0.77
    Ok
    0.75
    https
    0.75
    “
    0.75
    Act Density 0.444%

    No Known Activations