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

    Neuronpedia

    INDEX
    Explanations

    work and commitments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Turner
    0.35
     FDA
    0.35
     কলা
    0.35
     Von
    0.34
     Bell
    0.34
     Hofmann
    0.33
    を使用した
    0.33
     Hil
    0.32
     observé
    0.32
    沦
    0.32
    POSITIVE LOGITS
     obligations
    1.27
     commitments
    1.20
     obligaciones
    1.09
     Obligations
    0.97
     deadlines
    0.96
    忙
    0.96
     respons
    0.94
     workload
    0.93
     busy
    0.93
     tarefas
    0.92
    Act Density 0.047%

    No Known Activations