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

    Neuronpedia

    INDEX
    Explanations

    workplace collaboration and information requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revelations
    0.49
     insults
    0.49
     gorges
    0.49
     repression
    0.48
     isomeric
    0.48
     betrayal
    0.48
     grotes
    0.47
     museums
    0.47
     bleak
    0.47
     scenery
    0.46
    POSITIVE LOGITS
     업무
    0.95
    同事
    0.91
     colleagues
    0.82
     team
    0.82
     colleague
    0.81
     Team
    0.78
     टीम
    0.77
    团队
    0.76
    协作
    0.76
    Team
    0.75
    Act Density 0.297%

    No Known Activations