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

    Neuronpedia

    INDEX
    Explanations

    lack of personal states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gesto
    0.62
     deepening
    0.59
     नृत्य
    0.58
     gestures
    0.58
     misunder
    0.56
     oxides
    0.56
     penjelasan
    0.55
     utterances
    0.55
     জানানো
    0.55
     encoded
    0.55
    POSITIVE LOGITS
     coscienza
    0.88
     conciencia
    0.79
     consciousness
    0.77
     conscience
    0.75
     plantilla
    0.74
    прия
    0.68
     consciência
    0.68
     bewust
    0.66
    consciousness
    0.65
     quieres
    0.64
    Act Density 0.134%

    No Known Activations