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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Heating
    0.99
    Identifying
    0.99
    3
    0.94
    4
    0.94
    2
    0.91
     Моло
    0.90
    6
    0.89
    7
    0.88
    5
    0.87
    1
    0.87
    POSITIVE LOGITS
    mdan
    1.02
     Vorteil
    1.00
    ヽ
    0.94
    negara
    0.94
    arxiv
    0.93
    holders
    0.91
    vious
    0.89
     Rican
    0.89
    றவு
    0.88
    untza
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.