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

    Neuronpedia

    INDEX
    Explanations

    job/plan/proposal headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
     rnorm
    0.46
     devs
    0.45
    具体的な
    0.44
     guy
    0.43
     মুজিবকে
    0.43
     matchup
    0.42
     coalgebra
    0.42
     upregulation
    0.42
     changeset
    0.42
    POSITIVE LOGITS
    </h2>
    0.69
    ↵
    0.66
    ↵↵
    0.65
    ↵↵↵
    0.61
    </h3>
    0.57
    ــــ
    0.56
    ـــ
    0.54
                     
    0.52
                                   
    0.48
    ــ
    0.47
    Act Density 0.012%

    No Known Activations