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

    Neuronpedia

    INDEX
    Explanations

    references to memory management functions or methods

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

    dispose method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     religieuse
    -0.39
     unen
    -0.36
    vité
    -0.35
    íra
    -0.35
    iconque
    -0.34
    fighter
    -0.33
     étranger
    -0.33
    ্
    -0.33
     når
    -0.33
    grès
    -0.33
    POSITIVE LOGITS
    dispose
    3.14
     dispose
    1.92
     disposed
    1.43
    disposed
    1.34
    Disposed
    1.30
     disposing
    1.30
    disposing
    1.18
     Dispose
    1.16
     disposal
    1.15
     dispos
    1.13
    Act Density 0.001%

    No Known Activations