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

    Neuronpedia

    INDEX
    Explanations

    concepts related to independence and maintaining personal integrity

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

    maintaining independence and integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vis
    -0.33
     bono
    -0.31
     glas
    -0.26
     chip
    -0.26
     أم
    -0.25
    你了
    -0.25
     مط
    -0.25
     plane
    -0.25
     sic
    -0.24
    vis
    -0.24
    POSITIVE LOGITS
    SharedDtor
    0.60
    genodigd
    0.59
     increí
    0.59
     mantenere
    0.59
    protoimpl
    0.57
    writeFieldEnd
    0.57
    Resist
    0.56
    invokeLater
    0.56
     Avoiding
    0.56
     незавершена
    0.55
    Act Density 0.071%

    No Known Activations