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

    Neuronpedia

    INDEX
    Explanations

    taming, training, server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     globally
    0.49
     Citt
    0.47
     volcano
    0.45
     mangrove
    0.45
     खोसला
    0.45
     Flowering
    0.43
     wszyscy
    0.43
     mountain
    0.43
     Whilst
    0.43
     globalization
    0.42
    POSITIVE LOGITS
    a
    0.51
    o
    0.45
     подклю
    0.44
     ограничењима
    0.43
    ه
    0.43
    ×
    0.43
    ](
    0.42
    apun
    0.42
    垐
    0.42
     уда
    0.42
    Act Density 0.000%

    No Known Activations