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

    Neuronpedia

    INDEX
    Explanations

    writing down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENT
    0.83
    insertOne
    0.80
     extrap
    0.80
     ادار
    0.79
     embroidery
    0.78
    टीवी
    0.78
    Initi
    0.78
     flask
    0.77
     haki
    0.77
    Bottle
    0.77
    POSITIVE LOGITS
     down
    0.91
    itatively
    0.90
     Down
    0.88
     parv
    0.79
     منتقل
    0.78
    <unused2056>
    0.75
     సమీ
    0.74
     las
    0.74
    down
    0.73
     DOWN
    0.73
    Act Density 0.208%

    No Known Activations