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

    Neuronpedia

    INDEX
    Explanations

    functions and methods related to clearing resources or memory management

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

    Functions or methods for releasing/clearing memory

    np_acts-logits-general · gemini-2.0-flash

    clearing, closing, or freeing resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pits
    -0.56
    tadora
    -0.54
     Techn
    -0.51
    pits
    -0.49
     pits
    -0.49
     purest
    -0.48
     Thro
    -0.48
    pektrum
    -0.48
    cinia
    -0.48
     pit
    -0.47
    POSITIVE LOGITS
    enumi
    0.94
    GraphicsUnit
    0.75
    dropIfExists
    0.72
    SharedDtor
    0.70
    MemoryWarning
    0.69
    setVerticalGroup
    0.67
    usermodel
    0.66
    StructEnd
    0.65
    ьаж
    0.63
    脚注の使い方
    0.62
    Act Density 0.160%

    No Known Activations