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

    Neuronpedia

    INDEX
    Explanations

    Christian neutrality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ück
    0.54
    lh
    0.52
    ka
    0.49
    jan
    0.46
    ta
    0.46
    RODUCTION
    0.45
     jeden
    0.44
    侸
    0.44
    tal
    0.44
    lust
    0.44
    POSITIVE LOGITS
     سیاسی
    0.47
     spores
    0.47
     susceptibles
    0.47
    телям
    0.46
    یثیت
    0.45
     simbol
    0.44
     telep
    0.44
     dashes
    0.44
     cambiamenti
    0.43
     парни
    0.43
    Act Density 0.001%

    No Known Activations