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

    Neuronpedia

    INDEX
    Explanations

    business services

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catalyzes
    0.93
     lackluster
    0.93
     flavorful
    0.92
     catalyze
    0.87
     neighborhood
    0.83
     neighbors
    0.82
     rumors
    0.80
     tradeoffs
    0.79
     rumored
    0.78
     neighborhoods
    0.76
    POSITIVE LOGITS
    Whilst
    1.55
     recognises
    1.45
     standardised
    1.42
     personalised
    1.40
     Whilst
    1.40
     recognised
    1.38
     programme
    1.38
     bespoke
    1.38
     organisational
    1.34
     realisation
    1.34
    Act Density 0.119%

    No Known Activations