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

    Neuronpedia

    INDEX
    Explanations

    terms related to control and monitoring aspects

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

    outrebounded, 控底, 検出

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Zalety
    -0.44
     nôtre
    -0.43
    tgär
    -0.42
    }}}}
    -0.42
     Kebijakan
    -0.41
     vôtre
    -0.39
     convento
    -0.38
    +/*
    -0.38
    zieli
    -0.37
     Bürgermeister
    -0.37
    POSITIVE LOGITS
    ค
    2.30
     ค
    1.52
    ຄ
    0.80
    บค
    0.65
    คล
    0.64
     c
    0.60
     C
    0.57
     للمعارف
    0.55
    tisgarh
    0.53
     Cc
    0.52
    Act Density 0.000%

    No Known Activations