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

    Neuronpedia

    INDEX
    Explanations

    references to religious or spiritual beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    organisation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.56
    ſelf
    -0.56
    ſelves
    -0.54
     myſelf
    -0.53
    NUMX
    -0.50
    retanto
    -0.49
     menetap
    -0.46
     ſte
    -0.46
    ابراین
    -0.45
     ſta
    -0.44
    POSITIVE LOGITS
     surla
    0.60
    AxisAlignment
    0.50
     offence
    0.46
    Organis
    0.46
     organisation
    0.46
     randomised
    0.45
     SwiftUI
    0.44
     organisational
    0.44
     يتيمه
    0.43
     mand
    0.42
    Act Density 0.052%

    No Known Activations