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

    Neuronpedia

    INDEX
    Explanations

    navmesh pathfinding maze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    locks
    0.58
    ryption
    0.57
     Logical
    0.55
    et
    0.55
     Mixtures
    0.53
    nym
    0.53
    gy
    0.52
    synthetic
    0.52
    िंग्स
    0.52
     Flexible
    0.52
    POSITIVE LOGITS
     м
    0.75
     nonché
    0.64
     hâ
    0.63
    ਾ
    0.63
     م
    0.62
    у
    0.61
     通勤
    0.60
     ра
    0.60
     також
    0.60
     şehir
    0.59
    Act Density 0.017%

    No Known Activations