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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to important individuals or figures

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

    starts with J or wh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.47
    balleur
    -0.41
     EconPapers
    -0.39
    otheek
    -0.35
     ännu
    -0.34
    EDEFAULT
    -0.34
    脚注の使い方
    -0.34
    tvguidetime
    -0.34
     autorytatywna
    -0.33
     fournisseurs
    -0.33
    POSITIVE LOGITS
     যে
    0.85
     જે
    0.79
     जो
    0.79
     जिन
    0.75
     जिस
    0.73
     akik
    0.72
     য
    0.66
     amely
    0.61
     जि
    0.60
     जहां
    0.60
    Act Density 0.011%

    No Known Activations