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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases expressing personal thoughts, experiences, or opinions

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

    Personal pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    attracts/invites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    memberOf
    -0.36
    comentario
    -0.35
     ujednoznacz
    -0.32
    도록
    -0.32
    ंदीखरीदारी
    -0.31
     vilja
    -0.31
     contribuye
    -0.31
    DataAnnotations
    -0.31
    олові
    -0.31
    SystemColors
    -0.30
    POSITIVE LOGITS
     attracting
    0.80
     attract
    0.74
     attracts
    0.73
    吸引
    0.62
     ब्रेकडाउन
    0.60
    aarrggbb
    0.60
     atraer
    0.58
     invitar
    0.58
     sells
    0.57
    AddTagHelper
    0.57
    Act Density 0.614%

    No Known Activations