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

    Neuronpedia

    INDEX
    Explanations

    closing braces and conditional statements in code

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

    code comments and loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.50
     كومونز
    -0.47
    RegressionTest
    -0.46
     snippetHide
    -0.44
    FormsModule
    -0.42
    celotti
    -0.42
    ViewInit
    -0.40
    ReusableCell
    -0.40
    省市镇
    -0.39
    bkz
    -0.38
    POSITIVE LOGITS
    }//
    0.60
     //
    0.51
    loop
    0.48
     autorytatywna
    0.47
     loop
    0.47
     #
    0.41
     loops
    0.41
    Loop
    0.40
    ><!--
    0.40
     (#
    0.40
    Act Density 0.037%

    No Known Activations