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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to matrix operations and computational frameworks

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

    algorithmic techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.57
     queſta
    -0.56
     privées
    -0.52
     AssemblyCulture
    -0.49
     automatiques
    -0.49
     niech
    -0.48
     femininos
    -0.48
     électroniques
    -0.48
     alimentaires
    -0.47
     graphiques
    -0.46
    POSITIVE LOGITS
     techniques
    0.56
     technique
    0.54
    transQ
    0.53
     Techniques
    0.48
     approach
    0.47
    techniques
    0.47
    方法
    0.45
    +:+
    0.45
     jadx
    0.44
    advanced
    0.44
    Act Density 0.109%

    No Known Activations