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

    Neuronpedia

    INDEX
    Explanations

    cost-effective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    씩
    1.52
    1.30
     elastomers
    1.27
     uveden
    1.24
    erin
    1.23
    ありました
    1.21
    Trước
    1.20
    Ϝ
    1.20
    hare
    1.18
    hag
    1.17
    POSITIVE LOGITS
    א
    1.89
    á
    1.88
    ית
    1.63
    ното
    1.55
    ological
    1.51
    りの
    1.47
    ной
    1.45
    ناک
    1.45
    يم
    1.43
    نا
    1.42
    Act Density 0.158%

    No Known Activations