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

    Neuronpedia

    INDEX
    Explanations

    these dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     굉장히
    0.55
     issus
    0.52
     mittlerweile
    0.52
     unglaublich
    0.49
     clazz
    0.49
     maja
    0.48
     হয়ত
    0.48
     hea
    0.47
     चम्म
    0.47
     पंडित
    0.46
    POSITIVE LOGITS
     unavoid
    0.67
    persons
    0.60
     inescap
    0.58
     persisting
    0.57
     &/
    0.57
     healthful
    0.56
     Evidently
    0.52
     habitually
    0.51
    Persons
    0.50
     customarily
    0.50
    Act Density 0.005%

    No Known Activations