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

    Neuronpedia

    INDEX
    Explanations

    functional programming constructs, particularly those related to functions and their syntax

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

    reducing or summation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.76
     $_"
    -0.73
    GOTREF
    -0.71
     contextLoads
    -0.68
     queſta
    -0.67
    ChildScrollView
    -0.66
    Personendaten
    -0.66
     anún
    -0.66
    PerformLayout
    -0.65
    ंदीखरीदारी
    -0.64
    POSITIVE LOGITS
    reduce
    0.59
     reduce
    0.52
    Reduce
    0.51
     Reduce
    0.50
    <bos>
    0.47
     reduction
    0.47
     Redu
    0.44
     redu
    0.43
     reduced
    0.43
     reduces
    0.42
    Act Density 0.002%

    No Known Activations