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

    Neuronpedia

    INDEX
    Explanations

    maintaining data quality and consistency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coordinating
    0.48
     monitoring
    0.48
     Sometimes
    0.47
     coordinator
    0.47
     complex
    0.47
     strateg
    0.46
     assisting
    0.46
     Monitoring
    0.46
     mergers
    0.46
     overseeing
    0.45
    POSITIVE LOGITS
     japonicus
    0.54
     normas
    0.53
     disgraceful
    0.52
    rocities
    0.51
     tarses
    0.51
     norms
    0.50
     norme
    0.49
     shameful
    0.48
     cleanliness
    0.47
     cowardly
    0.47
    Act Density 0.099%

    No Known Activations