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

    Neuronpedia

    INDEX
    Explanations

    reservoir, backed, fear, gain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пка
    0.47
    ನಗೆ
    0.46
    њима
    0.46
    getMonth
    0.45
    이드
    0.44
    вале
    0.44
    Product
    0.43
    bouquet
    0.43
    пки
    0.43
    capt
    0.42
    POSITIVE LOGITS
     furtherance
    0.50
     skepticism
    0.44
     as
    0.44
     Trains
    0.43
    ര്‍
    0.43
     tensions
    0.43
     Space
    0.43
     n
    0.42
     Kom
    0.42
     yy
    0.42
    Act Density 0.004%

    No Known Activations