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

    Neuronpedia

    INDEX
    Explanations

    code snippets or constructs that indicate variable declarations or definitions

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

    start of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amazonaws
    -0.51
    ruik
    -0.50
    WillAppear
    -0.48
     Italijani
    -0.48
     فريبيس
    -0.47
    GHIJKLM
    -0.47
    yarnpkg
    -0.45
    あら
    -0.44
    Toponymie
    -0.44
    relativeTime
    -0.44
    POSITIVE LOGITS
     informée
    0.42
    énario
    0.40
    AppCompatTheme
    0.38
     AppComponent
    0.38
     Myself
    0.37
     GenerationType
    0.35
    Myself
    0.34
    RegressionTest
    0.34
    省市镇
    0.34
    否
    0.34
    Act Density 0.004%

    No Known Activations