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

    Neuronpedia

    INDEX
    Explanations

    routing and residential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Integrative
    0.41
     ارزش
    0.38
    椇
    0.38
     విలువ
    0.38
    ल्पनिक
    0.37
    と思いますが
    0.37
     मूल्य
    0.36
    ின்ன
    0.35
     кури
    0.35
     ಹಾಕ
    0.35
    POSITIVE LOGITS
     ale
    0.42
    ENTY
    0.41
     vague
    0.38
    Frost
    0.37
     Ale
    0.37
     general
    0.36
    reiber
    0.36
    极
    0.36
    depth
    0.36
     swell
    0.35
    Act Density 0.000%

    No Known Activations