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

    Neuronpedia

    INDEX
    Explanations

    social and psychological processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correlation
    0.55
     Correlation
    0.52
    Correlation
    0.48
     histogram
    0.44
     Histogram
    0.44
     histograms
    0.43
     statist
    0.42
     estadísticas
    0.42
     statistics
    0.42
     statistical
    0.42
    POSITIVE LOGITS
    moder
    0.46
    process
    0.45
     trajectories
    0.45
     thwarted
    0.45
     moderated
    0.44
     dyads
    0.44
     nascent
    0.42
     malad
    0.42
     processo
    0.41
     PROCESS
    0.41
    Act Density 0.012%

    No Known Activations