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

    Neuronpedia

    INDEX
    Explanations

    logical statements and speculations about consequences or predictions

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

    logical predictions or likelihoods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.52
    期刊论文
    -0.48
    evid
    -0.46
    DotNetBar
    -0.46
    PrintStream
    -0.43
    gment
    -0.43
    addGap
    -0.43
    舺
    -0.42
     essendo
    -0.41
     trebui
    -0.41
    POSITIVE LOGITS
    optionalTypeArgs
    0.41
    findpost
    0.39
    MessageOf
    0.36
     referrerpolicy
    0.34
    nodoc
    0.33
     архивлан
    0.33
     vars
    0.33
    coroutines
    0.33
     propos
    0.32
    LIM
    0.31
    Act Density 0.115%

    No Known Activations