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

    Neuronpedia

    INDEX
    Explanations

    references to group identity and inclusivity

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

    our, us, my, here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.36
    JsonPropertyName
    -0.33
     isComment
    -0.32
    ۣ
    -0.31
    Judge
    -0.31
    hängig
    -0.31
    Tikang
    -0.31
    にあります
    -0.30
     สาย
    -0.30
     between
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.56
     InputDecoration
    0.54
     CreateTagHelper
    0.53
    Enllaces
    0.49
     houſe
    0.48
    akhstan
    0.47
    AndEndTag
    0.46
    Invitation
    0.45
    EnableWeb
    0.45
     Majefty
    0.44
    Act Density 0.013%

    No Known Activations