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

    Neuronpedia

    INDEX
    Explanations

    vacuum pumps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powied
    0.84
    ق
    0.83
    cı
    0.74
    g
    0.70
    কার
    0.69
     destac
    0.68
    م
    0.68
    ക്ക്
    0.68
    j
    0.68
    ק
    0.68
    POSITIVE LOGITS
    ↵
    0.87
     at
    0.80
     for
    0.75
    .
    0.71
    0
    0.69
    个
    0.69
    ة
    0.66
     rutrum
    0.61
     on
    0.60
    TE
    0.59
    Act Density 0.010%

    No Known Activations