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

    Neuronpedia

    INDEX
    Explanations

    a positive outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thema
    0.89
    อย
    0.88
     efforts
    0.83
     dingen
    0.80
     wirkt
    0.80
     doings
    0.79
    chanics
    0.77
     Stuff
    0.76
     דבר
    0.74
     stuff
    0.74
    POSITIVE LOGITS
     glimpse
    1.51
     opportunity
    1.14
     glimpses
    1.05
    pportun
    1.04
    opportunity
    1.04
     oportunidade
    1.04
     overview
    0.98
     chance
    0.97
     invaluable
    0.97
     foothold
    0.96
    Act Density 0.098%

    No Known Activations