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

    Neuronpedia

    INDEX
    Explanations

    commands followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    퐫
    0.46
    $-,
    0.43
     Deployment
    0.42
    ?"
    0.40
    ិនបើ
    0.40
    ötzlich
    0.39
    ั้ย
    0.39
    ここでは
    0.39
    getFile
    0.39
    ဟုတ်
    0.39
    POSITIVE LOGITS
    :
    0.45
    ：
    0.44
     write
    0.43
     очеред
    0.43
     optim
    0.41
     लेख
    0.40
     מב
    0.39
     sar
    0.39
     guest
    0.39
    客
    0.38
    Act Density 0.000%

    No Known Activations