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

    Neuronpedia

    INDEX
    Explanations

    first [something]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ด์
    0.94
     bothering
    0.91
     jeste
    0.86
    ments
    0.85
    ter
    0.81
    斯
    0.80
     thuần
    0.79
     सस्ते
    0.79
    어도
    0.79
    ಮಾ
    0.78
    POSITIVE LOGITS
    ه
    1.01
    ᴇ
    0.85
     Else
    0.85
     shelled
    0.83
     Şimdi
    0.81
     Deploy
    0.79
     Dodson
    0.79
    ʙ
    0.78
    𝑧
    0.78
     Rodeo
    0.77
    Act Density 0.078%

    No Known Activations