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

    Neuronpedia

    INDEX
    Explanations

    added value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foundational
    1.03
     inherently
    0.97
     thoughtfully
    0.92
     perplexing
    0.91
     repur
    0.87
     egregious
    0.87
     factored
    0.82
     relatable
    0.82
     cognizant
    0.82
     licensure
    0.82
    POSITIVE LOGITS
     touristic
    2.06
     gastronomic
    1.95
     gastronomy
    1.79
     nowadays
    1.60
     solidarity
    1.60
     Unesco
    1.59
     envisaged
    1.53
     Luxembourg
    1.50
     nº
    1.49
     AcOEt
    1.48
    Act Density 0.690%

    No Known Activations