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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    Gratitude or appreciation expressed with "thank" variants

    np_acts-logits-general · gemini-2.0-flash

    expressions of thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.53
     externi
    -0.51
    $_['
    -0.51
    LabelTagHelper
    -0.50
    Brainz
    -0.50
    HeaderText
    -0.49
     CURIAM
    -0.49
    Пусть
    -0.49
    rostis
    -0.49
    principalTable
    -0.48
    POSITIVE LOGITS
    fjspx
    0.61
     kaarangay
    0.59
     begge
    0.56
     insightful
    0.56
     båda
    0.54
     aclar
    0.54
    Ambos
    0.53
     Chwiliwch
    0.53
     addSubview
    0.51
     rağmen
    0.49
    Act Density 0.070%

    No Known Activations