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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols in technical content

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

    citations and academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.85
     queſta
    -0.82
    SerializedSize
    -0.81
    arangay
    -0.79
    pecabe
    -0.75
    rungsseite
    -0.75
    PreferredItem
    -0.73
     propOrder
    -0.72
    GraphicsUnit
    -0.71
    RegressionTest
    -0.69
    POSITIVE LOGITS
    }{*}{}
    0.40
                
    0.37
     Ain
    0.36
    Ain
    0.36
    }{*}{
    0.36
    0.35
    0.34
            
    0.34
    Text
    0.34
    IN
    0.33
    Act Density 0.006%

    No Known Activations