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

    Neuronpedia

    INDEX
    Explanations

    conservative Christian values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mansfield
    0.50
    helby
    0.45
     mandat
    0.45
     FileReader
    0.41
     नॉ
    0.40
     Chesterfield
    0.39
    亢
    0.39
     videre
    0.39
    ობს
    0.39
     ஆல்
    0.38
    POSITIVE LOGITS
     walked
    0.48
     stepped
    0.39
    Din
    0.39
     Evening
    0.38
    \)
    0.38
     tenido
    0.36
     Pink
    0.36
    と思った
    0.36
     walk
    0.35
    DIN
    0.35
    Act Density 0.000%

    No Known Activations