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

    Neuronpedia

    INDEX
    Explanations

    technical or factual contexts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preservar
    0.68
     heresy
    0.61
    segaretro
    0.59
    vVertex
    0.59
    arrivalTime
    0.59
    듭
    0.59
    󠁣
    0.59
    berra
    0.59
     largeur
    0.59
    pyridin
    0.59
    POSITIVE LOGITS
     recently
    0.68
     who
    0.64
     treatment
    0.64
     team
    0.63
    kim
    0.63
     earned
    0.61
    way
    0.61
     lately
    0.61
    who
    0.59
    well
    0.59
    Act Density 0.001%

    No Known Activations