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

    Neuronpedia

    INDEX
    Explanations

    statements related to social interactions and personal beliefs

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

    people and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     merce
    -0.37
     Clegg
    -0.36
     intérêts
    -0.35
     ogen
    -0.34
    piel
    -0.34
     window
    -0.33
     miljø
    -0.33
    间
    -0.33
     menem
    -0.33
     handen
    -0.33
    POSITIVE LOGITS
     people
    0.84
     peoples
    0.76
    people
    0.76
    People
    0.73
     människor
    0.72
     People
    0.71
     PEOPLE
    0.69
    PEOPLE
    0.68
    Parcelize
    0.68
    stateProvider
    0.66
    Act Density 0.171%

    No Known Activations