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

    Neuronpedia

    INDEX
    Explanations

    references to specific products or items, particularly in the context of personal experiences or recommendations

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

    looks promising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.60
    GEBURTSDATUM
    -0.52
     wireType
    -0.48
    ransition
    -0.46
    sidemargin
    -0.46
     चीज़ों
    -0.45
    Географија
    -0.43
    OCCURRED
    -0.43
    clusal
    -0.43
     оригіналу
    -0.42
    POSITIVE LOGITS
    看起來
    0.99
     promises
    0.92
     looks
    0.91
     promising
    0.91
    looks
    0.89
    promises
    0.86
    看起来
    0.86
    Looks
    0.84
     seemed
    0.83
     Looks
    0.83
    Act Density 0.049%

    No Known Activations