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

    Neuronpedia

    INDEX
    Explanations

    questions and concepts related to social justice, rights, and moral decisions

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

    what is the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capucha
    -0.57
     miniaturka
    -0.55
     floresta
    -0.54
    elemField
    -0.54
     galinha
    -0.48
     amizade
    -0.47
    pecabe
    -0.47
    เอง
    -0.47
    itech
    -0.46
    AddHtmlAttribute
    -0.46
    POSITIVE LOGITS
    Jîn
    0.44
    Rüyada
    0.44
    ️
    0.40
    };*/
    0.39
    representative
    0.39
     socie
    0.39
     المعيارى
    0.38
    Denver
    0.38
     pap
    0.36
    Serv
    0.36
    Act Density 0.029%

    No Known Activations