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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional disconnect or societal critique

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

    immigration experts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limitaciones
    -0.33
     obstante
    -0.33
     tuttavia
    -0.31
     preocupaciones
    -0.31
     étendue
    -0.31
     difficultés
    -0.30
     continú
    -0.30
     natomiast
    -0.30
     ziyaret
    -0.29
     carattere
    -0.29
    POSITIVE LOGITS
     pinulongan
    0.81
     defaultstate
    0.76
    reportWebVitals
    0.71
     okuyayım
    0.68
    +#+
    0.65
     betweenstory
    0.64
    ьаж
    0.62
    Vidite
    0.61
    SizeF
    0.59
     resourceCulture
    0.59
    Act Density 0.002%

    No Known Activations