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

    Neuronpedia

    INDEX
    Explanations

    laws and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuevas
    0.66
     nový
    0.65
     nuevo
    0.59
     nuova
    0.59
     croissance
    0.59
     nové
    0.59
     nouvelle
    0.58
     reuniones
    0.56
     negocios
    0.55
     comunicaciones
    0.54
    POSITIVE LOGITS
     laws
    0.65
    L
    0.65
     अंतर्गत
    0.64
    Do
    0.60
    OD
    0.57
    RL
    0.55
    V
    0.55
     केले
    0.55
     standard
    0.54
    t
    0.54
    Act Density 0.071%

    No Known Activations