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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and positive sentiment

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

    love and positive reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SuspendLayout
    -0.36
    チー
    -0.35
     AspNetCore
    -0.35
    #+#
    -0.34
    ARAN
    -0.33
    蚪
    -0.33
     PM
    -0.33
     condition
    -0.32
    cookieParser
    -0.32
    log
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.68
    berdayakan
    0.58
     مشين
    0.57
    ſelf
    0.56
     Савезне
    0.55
     Gegenteil
    0.52
     MonoBehaviour
    0.51
    endpush
    0.49
     ioutil
    0.48
    poň
    0.48
    Act Density 0.006%

    No Known Activations