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

    Neuronpedia

    INDEX
    Explanations

    Tuesday

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    od
    1.00
    ou
    0.97
    er
    0.87
    op
    0.86
    ín
    0.84
    ow
    0.82
    ol
    0.79
    ot
    0.79
    oder
    0.77
    ário
    0.76
    POSITIVE LOGITS
    蛍光
    0.91
    Dropbox
    0.86
    бычно
    0.81
    нцикло
    0.78
    дне
    0.78
    ❒
    0.76
    朓
    0.76
    宻
    0.76
    MyToolkit
    0.75
    eyeglasses
    0.75
    Act Density 0.001%

    No Known Activations