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

    Neuronpedia

    INDEX
    Explanations

    foundations and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brownian
    0.50
    得很
    0.41
    星
    0.40
     আশ্বাস
    0.39
     इंजीनियरिंग
    0.38
     அறிவியல்
    0.38
     bitmaps
    0.38
     العلوم
    0.38
    Brown
    0.37
     হয়
    0.37
    POSITIVE LOGITS
    🍗
    0.52
     eigenen
    0.49
     own
    0.48
     yako
    0.48
    akuza
    0.47
    ards
    0.46
     włas
    0.46
     findest
    0.46
    🍖
    0.46
     herhangi
    0.46
    Act Density 0.016%

    No Known Activations