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

    Neuronpedia

    INDEX
    Explanations

    closest point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demarc
    0.53
     coarser
    0.52
     subsection
    0.50
     unjust
    0.48
     ponder
    0.48
     repatri
    0.48
     sensual
    0.47
     sharper
    0.47
     batsman
    0.47
     quarrel
    0.47
    POSITIVE LOGITS
    وان
    0.57
    l
    0.54
    R
    0.50
    ive
    0.48
    ierenden
    0.48
    도
    0.48
    Protein
    0.47
    ش
    0.47
    Healthy
    0.47
    ל
    0.46
    Act Density 0.001%

    No Known Activations