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

    Neuronpedia

    INDEX
    Explanations

    working with others or closely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Concerning
    0.70
    Course
    0.67
    Capable
    0.65
     colección
    0.64
    Cuando
    0.63
    Collection
    0.63
    Report
    0.62
    Importance
    0.62
     wyniku
    0.61
     electrónico
    0.61
    POSITIVE LOGITS
     tirelessly
    1.02
     collaboratively
    0.99
     actively
    0.96
     diligently
    0.89
     closely
    0.88
     cohes
    0.86
     intimately
    0.84
     cooper
    0.84
     out
    0.82
     financially
    0.76
    Act Density 0.642%

    No Known Activations