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

    positive feedback and gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.50
    IntoConstraints
    -0.46
    AccessorTable
    -0.40
     préstamos
    -0.37
    ByPrimaryKey
    -0.36
    baomidou
    -0.34
    dessous
    -0.34
     négo
    -0.34
     móvel
    -0.34
     minhas
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.54
    Personendaten
    0.50
     continúas
    0.49
    parsedMessage
    0.46
    Tikang
    0.46
     mergeFrom
    0.42
    Carriera
    0.42
     يتيمه
    0.41
    encodeWith
    0.41
     CallOverrides
    0.39
    Act Density 0.303%

    No Known Activations