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

    Neuronpedia

    INDEX
    Explanations

    etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     असून
    0.77
    :
    0.74
     gồm
    0.67
    either
    0.66
     |
    0.66
    ளான
    0.61
    }|
    0.61
    有两种
    0.59
     असलेल्या
    0.59
     झालेल्या
    0.58
    POSITIVE LOGITS
     etc
    6.21
    etc
    5.63
     Etc
    5.11
    等等
    5.06
     usw
    4.99
    等
    4.91
     ইত্যাদি
    4.88
     आदि
    4.78
    など
    4.77
     тощо
    4.75
    Act Density 1.330%

    No Known Activations