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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distract
    0.82
     distracting
    0.74
     venen
    0.73
     distracted
    0.72
     encaps
    0.71
     রহমানের
    0.69
    )':
    0.66
     impres
    0.66
     coincident
    0.66
     kiến
    0.66
    POSITIVE LOGITS
    qld
    0.87
    eten
    0.85
    toare
    0.85
    臬
    0.85
    անում
    0.84
    们
    0.84
    icu
    0.84
    unciation
    0.83
    onta
    0.83
    icole
    0.83
    Act Density 0.006%

    No Known Activations