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

    Neuronpedia

    INDEX
    Explanations

    date formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }_
    0.46
    epoch
    0.40
     decimal
    0.40
    鑑
    0.38
    UUID
    0.37
    ('_
    0.37
    toISOString
    0.37
    bo
    0.37
     والاح
    0.37
     위
    0.36
    POSITIVE LOGITS
     November
    0.53
     diciembre
    0.52
    📅
    0.52
    September
    0.51
    April
    0.48
    February
    0.47
     April
    0.47
    November
    0.47
     setembro
    0.46
     September
    0.45
    Act Density 0.012%

    No Known Activations