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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and their logical structures in code

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

    Code block control flow (if/else)

    np_acts-logits-general · gemini-2.0-flash

    code blocks and conditionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.61
     onPostExecute
    -0.57
     ujednoznacz
    -0.56
    EndContext
    -0.56
     استنادى
    -0.55
     kaarangay
    -0.55
    rungsseite
    -0.54
     informée
    -0.53
    sizeCache
    -0.53
     snippetHide
    -0.53
    POSITIVE LOGITS
    aarrggbb
    0.45
     unless
    0.39
    enumii
    0.39
     motivadoras
    0.36
    nteral
    0.35
     étages
    0.34
     InputDecoration
    0.33
     mayor
    0.33
    WRONG
    0.33
     épaules
    0.33
    Act Density 0.289%

    No Known Activations