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

    Neuronpedia

    INDEX
    Explanations

    conditional statements within programming code

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

    Keywords before "return" or "throw"

    np_acts-logits-general · gemini-2.0-flash

    spawn, restrictions, discrete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.74
     Efq
    -0.73
     يتيمه
    -0.66
    Geplaatst
    -0.64
     Shakspeare
    -0.61
    zysta
    -0.60
     faſt
    -0.59
     Enc
    -0.59
     Majefty
    -0.58
     AppColors
    -0.58
    POSITIVE LOGITS
    return
    1.07
     return
    0.90
     is
    0.77
     =
    0.74
     are
    0.64
    fromnode
    0.63
     be
    0.60
    MessageTagHelper
    0.58
    tagHelperRunner
    0.57
     was
    0.56
    Act Density 0.032%

    No Known Activations