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

    Neuronpedia

    INDEX
    Explanations

    after the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    过去
    0.48
     sedang
    0.47
     destiny
    0.46
     past
    0.46
    Result
    0.45
     trecut
    0.45
     beginnings
    0.44
     Anfang
    0.44
    Beginning
    0.43
     Beginning
    0.42
    POSITIVE LOGITS
     fact
    0.80
     conclusion
    0.69
     completion
    0.66
    fact
    0.63
    completion
    0.61
     expiration
    0.60
     conclusão
    0.59
     Fact
    0.58
    Fact
    0.58
     dust
    0.57
    Act Density 0.022%

    No Known Activations