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

    Neuronpedia

    INDEX
    Explanations

    racial, snow, mother, research, jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     некоторых
    0.46
     некоторы
    0.43
     SOLUTION
    0.42
     máxima
    0.42
     Systematic
    0.42
     Usual
    0.42
     Solvent
    0.41
     Skipping
    0.41
     SUBSTITUTE
    0.41
    оз
    0.40
    POSITIVE LOGITS
     fascism
    0.56
     sexuality
    0.54
    ImgBoard
    0.54
     gyne
    0.52
     binoculars
    0.51
     sex
    0.50
     hoodies
    0.49
    सेक्स
    0.49
     materiality
    0.47
    🗯
    0.47
    Act Density 0.001%

    No Known Activations