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

    Neuronpedia

    INDEX
    Explanations

    Results from studies and papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    扡
    0.44
    ᙱ
    0.42
    𝓪
    0.42
    谘
    0.42
    尟
    0.41
    扂
    0.41
    𝘸
    0.41
    損失
    0.40
    岖
    0.39
    𝙀
    0.39
    POSITIVE LOGITS
    Results
    0.58
     Results
    0.55
     Abbreviations
    0.48
     results
    0.48
     presents
    0.48
     authors
    0.47
    RESULTS
    0.47
    we
    0.46
     manuscript
    0.46
     herein
    0.45
    Act Density 0.007%

    No Known Activations