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

    Neuronpedia

    INDEX
    Explanations

    non-latin characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lla
    0.66
    infused
    0.64
    nder
    0.64
    raman
    0.62
    ested
    0.61
    ruta
    0.61
    ral
    0.61
    senz
    0.60
    epochs
    0.60
    feld
    0.60
    POSITIVE LOGITS
     hjälp
    0.72
    หรือ
    0.66
     我們
    0.62
     sogen
    0.61
     이
    0.61
    પણે
    0.60
     sagen
    0.60
     यस
    0.59
     뭐
    0.59
     П
    0.58
    Act Density 0.000%

    No Known Activations