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

    Neuronpedia

    INDEX
    Explanations

    evaluative expressions related to quality or enjoyment

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

    Hao residents,何時

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.58
    anthemum
    -0.49
    mappedBy
    -0.46
    municipi
    -0.45
     Wren
    -0.44
     Cyrus
    -0.42
    -------
    -0.42
     Lyra
    -0.42
     module
    -0.41
     PMC
    -0.40
    POSITIVE LOGITS
    好
    2.14
     好
    1.63
    我好
    1.26
    的好
    1.18
    Good
    1.09
     Good
    1.04
    good
    1.01
    有好
    0.99
     good
    0.95
     GOOD
    0.94
    Act Density 0.001%

    No Known Activations