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

    Neuronpedia

    INDEX
    Explanations

    curly brackets and associated variable declarations in code-related text

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

    code and serialization names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.73
     fashiola
    -0.62
    majánló
    -0.62
     }{@
    -0.61
     beſte
    -0.60
     betweenstory
    -0.60
     kasarigan
    -0.60
    endpush
    -0.60
     beſch
    -0.59
     zwiſchen
    -0.58
    POSITIVE LOGITS
    ksesta
    0.40
     igenom
    0.36
    SerializedName
    0.34
    ksessa
    0.33
     acabados
    0.32
    0.32
     varandra
    0.31
     finnas
    0.31
    そこは
    0.30
    tidaknya
    0.30
    Act Density 0.005%

    No Known Activations