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

    Neuronpedia

    INDEX
    Explanations

    social order and justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    পন্থী
    0.42
     policymakers
    0.39
    鸚
    0.38
    aucune
    0.38
    埋
    0.37
     StringIO
    0.37
    以後
    0.37
     preservatives
    0.37
     첨
    0.36
     none
    0.36
    POSITIVE LOGITS
    पत
    0.49
     surpre
    0.46
    Invisible
    0.45
    খন
    0.45
    Joy
    0.43
     projeto
    0.42
    Dont
    0.41
    极致
    0.41
    емых
    0.40
    Standing
    0.40
    Act Density 0.000%

    No Known Activations