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

    Neuronpedia

    INDEX
    Explanations

    emojis that express happiness or positivity

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

    emoticons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.53
    NewReader
    -0.51
     autorytatywna
    -0.51
    ValueStyle
    -0.50
    "){
    -0.49
    EndContext
    -0.48
    '){
    -0.46
     Мексичка
    -0.45
    ">
    -0.44
    \"");
    -0.44
    POSITIVE LOGITS
     lenker
    0.41
     跳转至
    0.39
     Erzb
    0.39
    appartamento
    0.38
     purpoſe
    0.37
    atmosfera
    0.37
    atteindre
    0.37
     AssemblyTitle
    0.37
     sanitaires
    0.36
     traductions
    0.35
    Act Density 0.036%

    No Known Activations