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

    Neuronpedia

    INDEX
    Explanations

    references to victims and acts of violence or abuse

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

    sexual acts involving her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     …
    -0.34
     too
    -0.32
     media
    -0.30
     laterales
    -0.28
     stora
    -0.28
     azules
    -0.27
     site
    -0.26
    ↵↵
    -0.25
     hard
    -0.25
     higher
    -0.25
    POSITIVE LOGITS
     ſein
    0.79
     ſind
    0.78
     queſta
    0.74
    pholes
    0.74
     ſei
    0.73
    باردا
    0.71
     témoig
    0.71
     ujednoznacz
    0.71
     stockbild
    0.70
     disambiguazione
    0.70
    Act Density 0.041%

    No Known Activations