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

    Neuronpedia

    INDEX
    Explanations

    blocking and obstruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disorientation
    0.50
     finiteness
    0.49
     bezpiecze
    0.48
     andre
    0.47
     baterías
    0.47
     integrity
    0.46
     üzere
    0.46
     as
    0.46
    stability
    0.46
    контро
    0.46
    POSITIVE LOGITS
     blocked
    0.95
     blocking
    0.94
     obstructing
    0.92
    阻
    0.92
     obstruct
    0.89
     Blocking
    0.88
     impediment
    0.83
     impede
    0.82
     blocker
    0.80
     obstructed
    0.80
    Act Density 0.077%

    No Known Activations