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

    Neuronpedia

    INDEX
    Explanations

    The Guardian articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     și
    0.54
     laborers
    0.50
     ț
    0.47
    वाड़ी
    0.47
     ज़
    0.46
     vapors
    0.46
     channeling
    0.46
     emphasized
    0.45
     neighboring
    0.45
     centered
    0.44
    POSITIVE LOGITS
     Fifa
    0.63
     polarisation
    0.58
     globalisation
    0.55
     recognises
    0.53
     Unesco
    0.53
     polarised
    0.50
     marginalised
    0.47
     recognise
    0.46
     scepticism
    0.46
     interviewee
    0.44
    Act Density 0.001%

    No Known Activations