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

    Neuronpedia

    INDEX
    Explanations

    limiting and restricting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tradición
    0.38
     dió
    0.37
     ChAT
    0.36
    ample
    0.36
     allClasses
    0.35
    ESSION
    0.35
     beats
    0.35
     CH
    0.34
    대
    0.34
    نية
    0.34
    POSITIVE LOGITS
     ограни
    0.95
     제한
    0.92
     सीमित
    0.89
     ограничен
    0.89
     ограничи
    0.86
     restricted
    0.86
     limited
    0.85
     restrict
    0.84
     limitar
    0.84
     restricting
    0.83
    Act Density 0.027%

    No Known Activations