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

    Neuronpedia

    INDEX
    Explanations

    the [religious noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ative
    0.33
     instead
    0.33
    (({
    0.33
    㧍
    0.33
     Potential
    0.32
    清晰
    0.32
     a
    0.32
     did
    0.32
    ,
    0.31
    ethe
    0.31
    POSITIVE LOGITS
    mselves
    0.49
     multitude
    0.44
     emberek
    0.41
     którym
    0.39
    ophylline
    0.39
     عدة
    0.38
     midst
    0.38
    ologically
    0.37
     epitome
    0.37
     heavens
    0.37
    Act Density 0.005%

    No Known Activations