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

    Neuronpedia

    INDEX
    Explanations

    assertions about potential outcomes and effectiveness regarding various subjects

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

    possibility and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.53
     resourceCulture
    -0.47
    prefixer
    -0.46
     useSelector
    -0.46
    apimachinery
    -0.45
     kaynağından
    -0.44
     defStyle
    -0.44
     getopt
    -0.44
     pinulongan
    -0.43
    internalType
    -0.42
    POSITIVE LOGITS
    addContainerGap
    0.49
    OuterAlt
    0.39
    RegressionTest
    0.39
    횟
    0.38
    发表于
    0.37
     akár
    0.36
     Consider
    0.36
    Ideally
    0.35
     Ideally
    0.35
    Enjoy
    0.34
    Act Density 0.053%

    No Known Activations