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

    Neuronpedia

    INDEX
    Explanations

    programming constructs, specifically control flow statements like conditionals and blocks of code

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

    code control flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verſ
    -0.75
    parsedMessage
    -0.74
    addPreferred
    -0.74
    ロウィン
    -0.73
     nakalista
    -0.73
    <unused51>
    -0.71
    <unused68>
    -0.71
    <unused41>
    -0.71
    <unused8>
    -0.71
    <unused23>
    -0.71
    POSITIVE LOGITS
    同
    0.26
     šk
    0.25
     fun
    0.25
    ModelAdmin
    0.24
     تضيفلها
    0.24
     sn
    0.23
     ever
    0.23
    zzleHttp
    0.22
     d
    0.22
    3
    0.22
    Act Density 0.013%

    No Known Activations