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

    Neuronpedia

    INDEX
    Explanations

    discussions about opinions and evaluations

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

    Follows conjunctions like "that" in different languages

    np_acts-logits-general · gemini-2.0-flash

    subordinate conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.92
    blurRadius
    -0.80
    parsedMessage
    -0.80
    windowFixed
    -0.75
    SizeMode
    -0.74
    AndEndTag
    -0.74
    脚注の使い方
    -0.73
     GenerationType
    -0.72
    verständlich
    -0.71
     EconPapers
    -0.71
    POSITIVE LOGITS
     что
    0.71
     que
    0.63
     що
    0.62
     hogy
    0.60
    ว่า
    0.55
     dass
    0.55
     že
    0.54
     ki
    0.52
     że
    0.51
     שב
    0.51
    Act Density 0.041%

    No Known Activations