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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values or structured data patterns

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

    static keyword usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.57
     AssemblyCulture
    -0.57
    ſelf
    -0.56
     ſta
    -0.56
    Autoritní
    -0.55
    posedge
    -0.55
     pleaſure
    -0.54
    DockStyle
    -0.54
     iprot
    -0.54
     ſte
    -0.53
    POSITIVE LOGITS
    èdia
    0.41
     vapa
    0.36
     scalar
    0.34
     spelers
    0.34
     schaffen
    0.33
     vertrouwen
    0.33
    ittens
    0.33
     keskus
    0.32
     caneta
    0.32
    hadores
    0.32
    Act Density 0.002%

    No Known Activations