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

    Neuronpedia

    INDEX
    Explanations

    defining abstract concepts and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mercado
    0.38
    :
    0.38
     vlastní
    0.36
     Mr
    0.36
     Pasar
    0.35
     careless
    0.34
    ニュアル
    0.34
     their
    0.34
     Martini
    0.34
     Morris
    0.34
    POSITIVE LOGITS
     που
    0.60
     الذي
    0.54
    which
    0.54
    that
    0.52
     التى
    0.51
    の一つ
    0.50
     التي
    0.49
     utilisé
    0.48
    whose
    0.48
     cuyos
    0.47
    Act Density 0.131%

    No Known Activations