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

    Neuronpedia

    INDEX
    Explanations

    from file, with cleaning, turned off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Authors
    0.41
    cienza
    0.41
    \}.
    0.40
     Camera
    0.39
     Communications
    0.38
    टु
    0.38
     автора
    0.38
     Annals
    0.38
     Horizons
    0.38
    Proceedings
    0.37
    POSITIVE LOGITS
     intoxicating
    0.41
     necessities
    0.38
     charset
    0.38
    city
    0.38
     potentiometer
    0.38
     unsatisfied
    0.38
    utet
    0.37
     apartamentos
    0.37
    代替
    0.36
     Damp
    0.36
    Act Density 0.000%

    No Known Activations