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

    Neuronpedia

    INDEX
    Explanations

    locations or contexts specified by the preposition "in"

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

    "in" followed by a preposition/noun

    np_acts-logits-general · gemini-2.0-flash

    in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    紹介します
    -0.67
    考える
    -0.65
    美国
    -0.60
    狙
    -0.59
     verrez
    -0.58
    principalTable
    -0.56
    urlopen
    -0.55
    Viitteet
    -0.55
    中国
    -0.54
    目指
    -0.54
    POSITIVE LOGITS
     addition
    1.33
     accordance
    1.32
     terms
    1.28
     relation
    1.24
     spite
    1.19
     lieu
    1.19
     conjunction
    1.19
     order
    1.12
     regards
    1.03
    jectable
    0.99
    Act Density 1.171%

    No Known Activations