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

    Neuronpedia

    INDEX
    Explanations

    numeric values and mathematical expressions or functions in the text

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

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interactiva
    -0.40
    Ārējās
    -0.36
     TestBed
    -0.36
     préférence
    -0.35
     limitée
    -0.35
     gesucht
    -0.34
     wiesz
    -0.34
     içinde
    -0.34
     znajdziesz
    -0.33
     ProtoMessage
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.59
    \{\\
    0.56
    UVWXYZ
    0.55
    WithIOException
    0.54
    parsedMessage
    0.54
    expandindo
    0.50
    WriteTagHelper
    0.49
     informée
    0.48
    WriteBarrier
    0.47
    URLException
    0.46
    Act Density 0.170%

    No Known Activations