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

    Neuronpedia

    INDEX
    Explanations

    map vs territory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     healing
    0.43
    enden
    0.43
    popo
    0.43
     healers
    0.43
     emergency
    0.41
     feeders
    0.41
     responders
    0.40
     buffered
    0.40
    rion
    0.40
    emergency
    0.39
    POSITIVE LOGITS
     уют
    0.44
     Ceramic
    0.42
     Productivity
    0.42
     Fossil
    0.41
    帔
    0.41
    মানব
    0.40
    ۇر
    0.40
     Italiano
    0.39
    畋
    0.39
    貿易
    0.39
    Act Density 0.000%

    No Known Activations