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

    Neuronpedia

    INDEX
    Explanations

    mentions of countries or regions, primarily focusing on their identifiers

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

    UK MPs, police, will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.72
    تقاوى
    -0.55
     Administrativna
    -0.54
    SequentialGroup
    -0.53
     Савезне
    -0.53
     xu
    -0.49
    -0.48
    writeFieldEnd
    -0.47
    DockStyle
    -0.46
     ProtoMessage
    -0.46
    POSITIVE LOGITS
    K
    0.71
    <bos>
    0.62
     K
    0.46
     counselor
    0.44
    vård
    0.41
    gulier
    0.40
    cookieParser
    0.39
    UK
    0.39
     contenus
    0.39
    Izvori
    0.39
    Act Density 0.004%

    No Known Activations