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

    Neuronpedia

    INDEX
    Explanations

    bubble wrap compression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assemblages
    0.52
     pept
    0.49
     specialization
    0.48
     artisans
    0.48
    reloadData
    0.47
     antit
    0.46
     spectrometers
    0.46
     ஆசிரிய
    0.46
     nontrivial
    0.46
     peptide
    0.46
    POSITIVE LOGITS
    。
    0.42
    政策
    0.41
    Proper
    0.41
    >(
    0.39
     hingegen
    0.39
    反而
    0.39
    政
    0.38
    Count
    0.38
    ="")
    0.38
     schme
    0.38
    Act Density 0.004%

    No Known Activations