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

    Neuronpedia

    INDEX
    Explanations

    mathematical constructs and terms related to functions, transformations, and polynomials

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    special characters or assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     im
    -0.51
     للمعارف
    -0.50
    '])){
    -0.46
    <eos>
    -0.46
     drop
    -0.45
    ./
    -0.44
    ）-
    -0.44
    orses
    -0.43
    allowNull
    -0.42
     dem
    -0.41
    POSITIVE LOGITS
    MemoryWarning
    0.76
     AssemblyCulture
    0.73
     Normdatei
    0.71
     :=
    0.69
     $=\
    0.66
     pleaſure
    0.66
     ::=
    0.64
    =(
    0.63
    TProtocol
    0.63
     vectorielle
    0.62
    Act Density 1.369%

    No Known Activations